GitHub topics: interpretability
SeldonIO/alibi
Algorithms for explaining machine learning models
Language: Python - Size: 30.3 MB - Last synced at: 38 minutes ago - Pushed at: 5 days ago - Stars: 2,500 - Forks: 257
jphall663/awesome-machine-learning-interpretability
A curated list of awesome responsible machine learning resources.
Size: 4.45 MB - Last synced at: 44 minutes ago - Pushed at: 27 days ago - Stars: 3,783 - Forks: 599
Dependable-Intelligent-Systems-Lab/xwhy
Explaining black boxes with a SMILE: Statistical Mode-agnostic Interpretability with Local Explanations
Language: JavaScript - Size: 24.9 MB - Last synced at: about 9 hours ago - Pushed at: about 10 hours ago - Stars: 10 - Forks: 2
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
Language: Jupyter Notebook - Size: 162 MB - Last synced at: about 9 hours ago - Pushed at: 2 months ago - Stars: 1,454 - Forks: 124
AdamCoscia/KnowledgeVIS
Visually compare fill-in-the-blank LLM prompts to uncover learned biases and associations!
Language: JavaScript - Size: 6.59 MB - Last synced at: about 14 hours ago - Pushed at: about 15 hours ago - Stars: 8 - Forks: 1
boniolp/kGraph
Graph Embedding for Interpretable Time Series Clustering
Language: Python - Size: 49.4 MB - Last synced at: about 17 hours ago - Pushed at: about 18 hours ago - Stars: 28 - Forks: 1
frgfm/torch-cam
Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)
Language: Python - Size: 10.1 MB - Last synced at: about 11 hours ago - Pushed at: 2 days ago - Stars: 2,189 - Forks: 220
hijohnnylin/neuronpedia
open source interpretability platform 🧠
Language: TypeScript - Size: 10.3 MB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 114 - Forks: 11
stellargraph/stellargraph
StellarGraph - Machine Learning on Graphs
Language: Python - Size: 92.5 MB - Last synced at: about 2 hours ago - Pushed at: about 1 year ago - Stars: 3,004 - Forks: 434
shap/shap
A game theoretic approach to explain the output of any machine learning model.
Language: Jupyter Notebook - Size: 301 MB - Last synced at: 1 day ago - Pushed at: 2 days ago - Stars: 23,858 - Forks: 3,359
ndif-team/nnsight
The nnsight package enables interpreting and manipulating the internals of deep learned models.
Language: Jupyter Notebook - Size: 49.8 MB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 562 - Forks: 50
jacobgil/pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Language: Python - Size: 134 MB - Last synced at: 2 days ago - Pushed at: about 1 month ago - Stars: 11,610 - Forks: 1,635
pytorch/captum
Model interpretability and understanding for PyTorch
Language: Python - Size: 306 MB - Last synced at: about 15 hours ago - Pushed at: 6 days ago - Stars: 5,209 - Forks: 517
sicara/tf-explain
Interpretability Methods for tf.keras models with Tensorflow 2.x
Language: Python - Size: 931 KB - Last synced at: 1 day ago - Pushed at: 11 months ago - Stars: 1,026 - Forks: 110
poloclub/webshap
JavaScript library to explain any machine learning models anywhere!
Language: TypeScript - Size: 35.5 MB - Last synced at: about 11 hours ago - Pushed at: about 2 years ago - Stars: 56 - Forks: 11
chaoyanghe/Awesome-Federated-Learning
FedML - The Research and Production Integrated Federated Learning Library: https://fedml.ai
Size: 210 KB - Last synced at: about 1 hour ago - Pushed at: over 2 years ago - Stars: 1,957 - Forks: 329
stanfordnlp/axbench
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
Language: Python - Size: 617 MB - Last synced at: about 2 hours ago - Pushed at: about 2 months ago - Stars: 78 - Forks: 6
boniolp/graphit
Graph-based Time Series Clustering Visualisation Tools
Language: Python - Size: 5.75 MB - Last synced at: 2 days ago - Pushed at: 3 days ago - Stars: 1 - Forks: 0
faded53222/NSWord
RNA Modification Detection using Nanopore Direct RNA Sequencing via improved Transformer
Language: Jupyter Notebook - Size: 19.1 MB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 2 - Forks: 0
stanfordnlp/pyreft
Stanford NLP Python library for Representation Finetuning (ReFT)
Language: Python - Size: 104 MB - Last synced at: about 14 hours ago - Pushed at: 3 months ago - Stars: 1,466 - Forks: 125
alvinwan/neural-backed-decision-trees
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
Language: Python - Size: 2.57 MB - Last synced at: 3 days ago - Pushed at: about 2 years ago - Stars: 621 - Forks: 132
iancovert/sage
For calculating global feature importance using Shapley values.
Language: Python - Size: 7.93 MB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 270 - Forks: 35
vanderschaarlab/autoprognosis
A system for automating the design of predictive modeling pipelines tailored for clinical prognosis.
Language: Python - Size: 960 KB - Last synced at: 1 day ago - Pushed at: about 2 months ago - Stars: 147 - Forks: 28
google-deepmind/penzai
A JAX research toolkit for building, editing, and visualizing neural networks.
Language: Python - Size: 484 MB - Last synced at: about 7 hours ago - Pushed at: 18 days ago - Stars: 1,779 - Forks: 62
g8a9/ferret
A python package for benchmarking interpretability techniques on Transformers.
Language: Python - Size: 1.52 MB - Last synced at: about 5 hours ago - Pushed at: 8 months ago - Stars: 211 - Forks: 15
SteveKGYang/MentalLLaMA
This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.
Language: Python - Size: 13.2 MB - Last synced at: 3 days ago - Pushed at: about 1 year ago - Stars: 260 - Forks: 27
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
Language: Jupyter Notebook - Size: 61.8 MB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 2,872 - Forks: 346
IAAR-Shanghai/Awesome-Attention-Heads
An awesome repository & A comprehensive survey on interpretability of LLM attention heads.
Language: TeX - Size: 6.07 MB - Last synced at: 4 days ago - Pushed at: 2 months ago - Stars: 348 - Forks: 12
ZFancy/awesome-activation-engineering
A curated list of resources for activation engineering
Size: 174 KB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 69 - Forks: 1
ML4BM-Lab/SENA
Official repository for the SENA-discrepancy-VAE model.
Language: Python - Size: 27.3 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 4 - Forks: 1
interpretml/interpret
Fit interpretable models. Explain blackbox machine learning.
Language: C++ - Size: 14.7 MB - Last synced at: 2 days ago - Pushed at: 19 days ago - Stars: 6,486 - Forks: 746
bartbussmann/BatchTopK
Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
Language: Python - Size: 22.5 KB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 38 - Forks: 6
evandez/neuron-descriptions
Natural Language Descriptions of Deep Visual Features, ICLR 2022
Language: Python - Size: 3.04 MB - Last synced at: 4 days ago - Pushed at: almost 2 years ago - Stars: 65 - Forks: 7
DavidUdell/sparse_circuit_discovery
Circuit discovery in GPT-2 small, using sparse autoencoding
Language: Python - Size: 19.2 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 7 - Forks: 1
nathanwang16/Fractal
Models learn representations, and world patterns. Fractal is beautiful, but not the key.
Language: Jupyter Notebook - Size: 4.47 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 0 - Forks: 0
ndif-team/ndif-website
The website for NDIF, the National Deep Inference Fabric
Language: HTML - Size: 39.8 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 2 - Forks: 1
EthicalML/xai
XAI - An eXplainability toolbox for machine learning
Language: Python - Size: 17.8 MB - Last synced at: 5 days ago - Pushed at: over 3 years ago - Stars: 1,168 - Forks: 179
ndif-team/ndif
The NDIF server, which performs deep inference and serves nnsight requests remotely
Language: Python - Size: 18.6 MB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 25 - Forks: 7
microsoft/responsible-ai-toolbox
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.
Language: TypeScript - Size: 111 MB - Last synced at: 6 days ago - Pushed at: 3 months ago - Stars: 1,529 - Forks: 402
google/yggdrasil-decision-forests
A library to train, evaluate, interpret, and productionize decision forest models such as Random Forest and Gradient Boosted Decision Trees.
Language: C++ - Size: 39.5 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 569 - Forks: 60
Oxid15/xai-benchmark
Open and extensible benchmark for XAI methods
Language: Python - Size: 1.78 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 6 - Forks: 0
wangyongjie-ntu/Awesome-explainable-AI
A collection of research materials on explainable AI/ML
Language: Markdown - Size: 1.93 MB - Last synced at: 6 days ago - Pushed at: about 2 months ago - Stars: 1,494 - Forks: 203
pietrobarbiero/pytorch_explain
PyTorch Explain: Interpretable Deep Learning in Python.
Language: Jupyter Notebook - Size: 42.1 MB - Last synced at: 3 days ago - Pushed at: 12 months ago - Stars: 154 - Forks: 14
EthicalML/awesome-production-machine-learning
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
Size: 2.36 MB - Last synced at: 7 days ago - Pushed at: 10 days ago - Stars: 18,412 - Forks: 2,342
tensorflow/decision-forests
A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in Keras.
Language: Python - Size: 5.87 MB - Last synced at: 6 days ago - Pushed at: about 1 month ago - Stars: 680 - Forks: 113
ModelOriented/hstats
Friedman's H-statistics
Language: R - Size: 217 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 30 - Forks: 1
understandable-machine-intelligence-lab/Quantus
Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
Language: Jupyter Notebook - Size: 147 MB - Last synced at: 6 days ago - Pushed at: 3 months ago - Stars: 598 - Forks: 77
ModelOriented/DALEX
moDel Agnostic Language for Exploration and eXplanation
Language: Python - Size: 798 MB - Last synced at: 4 days ago - Pushed at: 3 months ago - Stars: 1,420 - Forks: 168
tensorflow/tcav
Code for the TCAV ML interpretability project
Language: Jupyter Notebook - Size: 625 KB - Last synced at: 6 days ago - Pushed at: 10 months ago - Stars: 640 - Forks: 152
mmschlk/shapiq
Shapley Interactions and Shapley Values for Machine Learning
Language: Python - Size: 309 MB - Last synced at: 8 days ago - Pushed at: 8 days ago - Stars: 514 - Forks: 34
jorge-martinez-gil/graphcodebert-interpretability
Augmenting the Interpretability of GraphCodeBERT for Code Similarity Tasks
Language: Python - Size: 9.71 MB - Last synced at: 8 days ago - Pushed at: 8 days ago - Stars: 5 - Forks: 0
chr5tphr/zennit
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Language: Python - Size: 2.28 MB - Last synced at: 2 days ago - Pushed at: 10 months ago - Stars: 225 - Forks: 34
deel-ai/xplique
👋 Xplique is a Neural Networks Explainability Toolbox
Language: Python - Size: 33.4 MB - Last synced at: about 13 hours ago - Pushed at: 7 months ago - Stars: 688 - Forks: 58
stanfordnlp/pyvene
Stanford NLP Python library for understanding and improving PyTorch models via interventions
Language: Python - Size: 25.4 MB - Last synced at: about 14 hours ago - Pushed at: 13 days ago - Stars: 740 - Forks: 82
jasonjmcghee/livelove
Love2D LSP (VS Code / Neovim / Zed / etc.) extension for live coding and live variable tracking
Language: JavaScript - Size: 5.33 MB - Last synced at: 9 days ago - Pushed at: 9 days ago - Stars: 130 - Forks: 2
rmovva/HypotheSAEs
Hypothesizing interpretable relationships in text datasets using sparse autoencoders.
Language: Jupyter Notebook - Size: 11.5 MB - Last synced at: 9 days ago - Pushed at: 9 days ago - Stars: 24 - Forks: 2
bgreenwell/ebm
Explainable Boosting Machines
Language: R - Size: 44.5 MB - Last synced at: 6 days ago - Pushed at: 2 months ago - Stars: 3 - Forks: 1
KempnerInstitute/overcomplete
👋 Overcomplete is a Vision-based SAE Toolbox
Language: Python - Size: 57.2 MB - Last synced at: 7 days ago - Pushed at: about 2 months ago - Stars: 53 - Forks: 1
rigvedrs/YOLO-V11-CAM
Wanna know what your model sees? Here's a package for applying EigenCAM and generating heatmap from the new YOLO V11 model
Language: Jupyter Notebook - Size: 40 MB - Last synced at: 11 days ago - Pushed at: 11 days ago - Stars: 201 - Forks: 42
Sorades/CLAT
[TMI 2024] Code for "Concept-based Lesion Aware Transformer for Interpretable Retinal Disease Diagnosis"
Language: Python - Size: 617 KB - Last synced at: 12 days ago - Pushed at: 12 days ago - Stars: 19 - Forks: 0
ChicagoHAI/hypothesis-generation
This is the official repository for HypoGeniC (Hypothesis Generation in Context) and HypoRefine, which are automated, data-driven tools that leverage large language models to generate hypothesis for open-domain research. For more details, please see the original paper using the link below.
Language: Python - Size: 121 MB - Last synced at: 11 days ago - Pushed at: 11 days ago - Stars: 65 - Forks: 8
microsoft/automated-brain-explanations
Generating and validating natural-language explanations for the brain.
Language: Jupyter Notebook - Size: 1.06 GB - Last synced at: 1 day ago - Pushed at: about 2 months ago - Stars: 52 - Forks: 6
poloclub/timbertrek
Explore and compare 1K+ accurate decision trees in your browser!
Language: TypeScript - Size: 36.9 MB - Last synced at: 6 days ago - Pushed at: about 1 year ago - Stars: 161 - Forks: 10
tensorflow/lucid 📦
A collection of infrastructure and tools for research in neural network interpretability.
Language: Jupyter Notebook - Size: 141 MB - Last synced at: 6 days ago - Pushed at: over 2 years ago - Stars: 4,694 - Forks: 654
PKU-Alignment/aligner
[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct
Language: Python - Size: 16.3 MB - Last synced at: 7 days ago - Pushed at: 4 months ago - Stars: 170 - Forks: 8
JoaoLages/diffusers-interpret
Diffusers-Interpret 🤗🧨🕵️♀️: Model explainability for 🤗 Diffusers. Get explanations for your generated images.
Language: Jupyter Notebook - Size: 77.5 MB - Last synced at: about 9 hours ago - Pushed at: over 2 years ago - Stars: 276 - Forks: 14
trustyai-explainability/trustyai-explainability
TrustyAI Explainability Toolkit
Language: Java - Size: 19 MB - Last synced at: 14 days ago - Pushed at: 14 days ago - Stars: 39 - Forks: 42
JHoelli/Awesome-Time-Series-Explainability
A list of (post-hoc) XAI for time series
Size: 424 KB - Last synced at: 13 days ago - Pushed at: 8 months ago - Stars: 134 - Forks: 16
OpenMOSS/Language-Model-SAEs
For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
Language: Python - Size: 10.2 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 113 - Forks: 13
dobriban/Principles-of-AI-LLMs
Materials for the course Principles of AI: LLMs at UPenn (Stat 9911, Spring 2025). LLM architectures, training paradigms (pre- and post-training, alignment), test-time computation, reasoning, safety and robustness (jailbreaking, oversight, uncertainty), representations, interpretability (circuits), etc.
Size: 188 MB - Last synced at: 14 days ago - Pushed at: 14 days ago - Stars: 31 - Forks: 2
EleutherAI/knowledge-neurons
A library for finding knowledge neurons in pretrained transformer models.
Language: Python - Size: 11.6 MB - Last synced at: 6 days ago - Pushed at: about 3 years ago - Stars: 157 - Forks: 18
dmis-lab/Monet
[ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers
Language: Python - Size: 252 KB - Last synced at: 9 days ago - Pushed at: 4 months ago - Stars: 66 - Forks: 3
koulanurag/mmn
Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
Language: Python - Size: 115 MB - Last synced at: 4 days ago - Pushed at: over 2 years ago - Stars: 50 - Forks: 13
datamllab/awesome-fairness-in-ai
A curated list of awesome Fairness in AI resources
Size: 33.2 KB - Last synced at: 7 days ago - Pushed at: over 1 year ago - Stars: 320 - Forks: 65
eliaskempf/ideal_words
A PyTorch implementation of ideal word computation.
Language: Python - Size: 48.8 KB - Last synced at: 16 days ago - Pushed at: 16 days ago - Stars: 4 - Forks: 0
haofanwang/Awesome-Computer-Vision
Awesome Resources for Advanced Computer Vision Topics
Size: 93.8 KB - Last synced at: 8 days ago - Pushed at: over 2 years ago - Stars: 230 - Forks: 43
csinva/tree-prompt
Tree prompting: easy-to-use scikit-learn interface for improved prompting.
Language: Jupyter Notebook - Size: 18.2 MB - Last synced at: 15 days ago - Pushed at: over 1 year ago - Stars: 36 - Forks: 4
taufeeque9/codebook-features
Sparse and discrete interpretability tool for neural networks
Language: Python - Size: 3.58 MB - Last synced at: 4 days ago - Pushed at: about 1 year ago - Stars: 61 - Forks: 3
oneTaken/awesome_deep_learning_interpretability
深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码)
Size: 156 KB - Last synced at: 8 days ago - Pushed at: about 1 year ago - Stars: 747 - Forks: 122
ThyrixYang/awesome-artificial-intelligence-research
A curated list of Artificial Intelligence (AI) Research, tracks the cutting edge trending of AI research, including recommender systems, computer vision, machine learning, etc.
Size: 44.9 KB - Last synced at: 4 days ago - Pushed at: over 2 years ago - Stars: 124 - Forks: 14
ssfgunner/IIS
[ICLR 2025 Spotlight] This is the official repository for our paper: ''Enhancing Pre-trained Representation Classifiability can Boost its Interpretability''.
Language: Python - Size: 2.89 MB - Last synced at: 18 days ago - Pushed at: 18 days ago - Stars: 15 - Forks: 0
alanqrwang/keymorph
Robust multimodal image registration via keypoints
Language: Python - Size: 690 MB - Last synced at: 15 days ago - Pushed at: 9 months ago - Stars: 78 - Forks: 17
ALEX-nlp/MUI-Eval
Repository for the paper: Revisiting LLM Evaluation through Mechanism Interpretability: a New Metric and Model Utility Law
Language: Python - Size: 7.36 MB - Last synced at: 18 days ago - Pushed at: about 1 month ago - Stars: 7 - Forks: 0
BirkhoffG/Explainable-ML-Papers
A list of research papers of explainable machine learning.
Size: 13.7 KB - Last synced at: 6 days ago - Pushed at: almost 4 years ago - Stars: 36 - Forks: 3
salvatorecalderaro/geco_explainer
GECo algorithm for Graph Neural Networks Explaination
Language: Jupyter Notebook - Size: 390 KB - Last synced at: 19 days ago - Pushed at: 19 days ago - Stars: 1 - Forks: 0
zju-vipa/awesome-neural-trees
Introduction, selected papers and possible corresponding codes in our review paper "A Survey of Neural Trees"
Size: 1.66 MB - Last synced at: 4 days ago - Pushed at: over 2 years ago - Stars: 78 - Forks: 9
inseq-team/inseq
Interpretability for sequence generation models 🐛 🔍
Language: Python - Size: 7.64 MB - Last synced at: 19 days ago - Pushed at: 19 days ago - Stars: 412 - Forks: 37
M-Nauta/ProtoTree
ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Language: Python - Size: 870 KB - Last synced at: 6 days ago - Pushed at: almost 3 years ago - Stars: 101 - Forks: 21
linkedin/TE2Rules
Python library to explain Tree Ensemble models (TE) like XGBoost, using a rule list.
Language: Python - Size: 10.9 MB - Last synced at: 10 days ago - Pushed at: about 1 year ago - Stars: 55 - Forks: 6
GnanaPrakashSG2004/Concept_Distillation
Framework to distill concepts of a teacher model to a student model. Trying to understand impact on performance and interpretability of the distilled student model obtained from this training paradigm.
Language: Jupyter Notebook - Size: 71.8 MB - Last synced at: 9 days ago - Pushed at: 9 days ago - Stars: 0 - Forks: 0
ModelOriented/kernelshap
Different SHAP algorithms
Language: R - Size: 2.5 MB - Last synced at: 11 days ago - Pushed at: about 1 month ago - Stars: 47 - Forks: 7
DavidF-22/ARI3205-InterpretableAI_Project
This repository contains the entire codebase for the Interpretable AI Group Project. This project focuses on exploring and implementing multiple interpretability techniques in machine learning models to enhance transparency and interpretability
Language: Jupyter Notebook - Size: 3.32 MB - Last synced at: 21 days ago - Pushed at: 21 days ago - Stars: 1 - Forks: 0
fzi-forschungszentrum-informatik/TSInterpret
An Open-Source Library for the interpretability of time series classifiers
Language: Python - Size: 200 MB - Last synced at: about 2 hours ago - Pushed at: 6 months ago - Stars: 133 - Forks: 14
pralab/secml
A Python library for Secure and Explainable Machine Learning
Language: Jupyter Notebook - Size: 67.2 MB - Last synced at: 23 days ago - Pushed at: 4 months ago - Stars: 175 - Forks: 26
evan-lloyd/graphpatch
graphpatch is a library for activation patching on PyTorch neural network models.
Language: Python - Size: 4.49 MB - Last synced at: 6 days ago - Pushed at: 3 months ago - Stars: 14 - Forks: 0
BCG-X-Official/facet
Human-explainable AI.
Language: Jupyter Notebook - Size: 50.5 MB - Last synced at: 6 days ago - Pushed at: over 1 year ago - Stars: 520 - Forks: 47
ModelOriented/modelStudio
📍 Interactive Studio for Explanatory Model Analysis
Language: R - Size: 36.2 MB - Last synced at: 3 days ago - Pushed at: over 1 year ago - Stars: 332 - Forks: 32
ApocryphalEditor/SRM-mapping-framework
A framework for mapping the internal geometry of transformer representations using angular projection, neuron-level modulation, and epistemically grounded prompts. Based on and extending Bird's original Spotlight Resonance Method (SRM).
Language: Python - Size: 1.55 MB - Last synced at: 25 days ago - Pushed at: 25 days ago - Stars: 0 - Forks: 0
zjunlp/DynamicKnowledgeCircuits
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Language: Jupyter Notebook - Size: 39.4 MB - Last synced at: 25 days ago - Pushed at: 26 days ago - Stars: 30 - Forks: 0
Julia-XAI/ExplainableAI.jl
Explainable AI in Julia.
Language: Julia - Size: 41.6 MB - Last synced at: 4 days ago - Pushed at: about 1 month ago - Stars: 112 - Forks: 3
