An open API service providing repository metadata for many open source software ecosystems.

Topic: "sparse-autoencoders"

vgel/repeng

A library for making RepE control vectors

Language: Jupyter Notebook - Size: 299 KB - Last synced at: about 1 month ago - Pushed at: about 2 months ago - Stars: 649 - Forks: 50

ysh329/Chinese-UFLDL-Tutorial 📦

[UNMAINTAINED] 非监督特征学习与深度学习中文教程,该版本翻译自新版 UFLDL Tutorial 。建议新人们去学习斯坦福的CS231n课程,该门课程在网易云课堂上也有一个配有中文字幕的版本。

Size: 1.54 MB - Last synced at: 7 months ago - Pushed at: over 7 years ago - Stars: 352 - Forks: 118

OpenMOSS/Language-Model-SAEs

Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.

Language: Python - Size: 32.1 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 163 - Forks: 21

LahiruJayasinghe/DeepDOA

Finding Direction of arrival (DOA) of small UAVs using Sparse Denoising Autoencoders and Deep Neural Networks.

Language: Python - Size: 444 KB - Last synced at: over 1 year ago - Pushed at: about 7 years ago - Stars: 70 - Forks: 38

dmis-lab/Monet

[ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers

Language: Python - Size: 252 KB - Last synced at: 7 months ago - Pushed at: 10 months ago - Stars: 66 - Forks: 3

rmovva/HypotheSAEs

Hypothesizing interpretable relationships in text datasets using sparse autoencoders.

Language: Jupyter Notebook - Size: 16.5 MB - Last synced at: 22 days ago - Pushed at: 2 months ago - Stars: 55 - Forks: 18

neuroexplicit-saar/Discover-then-Name

Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.

Language: Python - Size: 1.59 MB - Last synced at: 2 months ago - Pushed at: about 1 year ago - Stars: 47 - Forks: 5

abhisheksambyal/Autoencoders-using-Pytorch-Medical-Imaging

Medical Imaging, Denoising Autoencoder, Sparse Denoising Autoencoder (SDAE) End-to-end and Layer Wise Pretraining

Language: Jupyter Notebook - Size: 10.9 MB - Last synced at: over 2 years ago - Pushed at: over 6 years ago - Stars: 38 - Forks: 10

Abhipanda4/Sparse-Autoencoders

Sparse Autoencoders using FashionMNIST dataset

Language: Python - Size: 41.3 MB - Last synced at: over 2 years ago - Pushed at: over 7 years ago - Stars: 31 - Forks: 3

dynamical-inference/patchsae

Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"

Language: Jupyter Notebook - Size: 14.8 MB - Last synced at: 19 days ago - Pushed at: 19 days ago - Stars: 28 - Forks: 3

meteahishali/SRL-SOA

Hyperspectral Band Selection using Self-Representation Learning with Sparse 1D-Operational Autoencoder (SRL-SOA)

Language: Python - Size: 862 KB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 22 - Forks: 7

Butanium/tiny-activation-dashboard

A tiny easily hackable implementation of a feature dashboard.

Language: Jupyter Notebook - Size: 127 KB - Last synced at: about 2 months ago - Pushed at: 2 months ago - Stars: 14 - Forks: 2

MaheepChaudhary/SAE-Ravel

Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the paper "Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small"

Language: Python - Size: 11.9 MB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 10 - Forks: 1

255BITS/sae-evolver

Use evolution with sparse autoencoders

Language: Python - Size: 86.9 KB - Last synced at: 3 months ago - Pushed at: 10 months ago - Stars: 4 - Forks: 0

MikolajSzawerda/music-sae

Sparse Autoencoders (SAEs) for unsupervised music representation learning.

Language: Jupyter Notebook - Size: 36.1 MB - Last synced at: 11 days ago - Pushed at: 12 days ago - Stars: 3 - Forks: 1

gkimer/thesis-ICI

Diagnóstico de falla de rodamiento utilizando descomposición modal empírica y deep learning

Language: Matlab - Size: 43.6 MB - Last synced at: over 2 years ago - Pushed at: over 7 years ago - Stars: 3 - Forks: 1

peppinob-ol/attribution-graph-probing

Automates attribution-graph analysis via probe prompting: circuit-trace a prompt, auto-generate concept probes, profile feature activations, cluster supernodes.

Language: Python - Size: 44.7 MB - Last synced at: about 13 hours ago - Pushed at: about 15 hours ago - Stars: 1 - Forks: 0

jwuphysics/euclid-galaxy-morphology-saes

studying (self-)supervised representations of Euclid galaxy imaging via SAEs

Language: Python - Size: 166 KB - Last synced at: 20 days ago - Pushed at: 20 days ago - Stars: 1 - Forks: 0

wasim/scaling-specialization-dense-lms

Do dense LMs develop MoE-like specialization as they scale? Measure it, visualize it, and turn it into speed.

Language: Python - Size: 6.84 KB - Last synced at: 23 days ago - Pushed at: 23 days ago - Stars: 1 - Forks: 0

Dhia-naouali/Tickling-Vision-Models

performing mechanistic interpretability on inceptionV1, from linear prob and sparse direction maximization to adversarial and ciruict patching & ablation

Language: Python - Size: 5.16 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0

ashioyajotham/exploring_saes

Implementation and analysis of Sparse Autoencoders for neural network interpretability research. Features interactive visualization dashboard and W&B integration.

Language: Python - Size: 59.7 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 1 - Forks: 2

jiaqingxie/steer-sae

Code for the ETH MSc Thesis: Sparse Autoencoders vs. Activation Difference for Language Model Steering

Language: Shell - Size: 9.66 MB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 1 - Forks: 0

krishnakanthnakka/MammoSAE

Official code release for the paper: "Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autonencoders"

Language: Python - Size: 34.1 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

lennart-finke/classifier-interp

Training Sparse Autoencoders on Prompt-Guard

Language: HTML - Size: 3.79 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

behroozazarkhalili/SAE-Transcoder

Unified SAE and Transcoder training using EleutherAI/sparsify library for neural network interpretability research

Language: Python - Size: 89.8 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

ashioyajotham/interp

My AI interpretability research journey

Language: HTML - Size: 22.2 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 0 - Forks: 0

Utkarshp1/EE-412-Neural-Networks-and-Deep-Learning

This repository is created as part of Neural Networks and Deep Learning course at my college. This repo contains the implementations of Neural Network and Deep Learning algorithms.

Language: Jupyter Notebook - Size: 2.19 MB - Last synced at: over 2 years ago - Pushed at: almost 4 years ago - Stars: 0 - Forks: 0

ghost1412/Keras-Autoencoder

Language: Python - Size: 23.4 KB - Last synced at: over 2 years ago - Pushed at: about 7 years ago - Stars: 0 - Forks: 0

martinkersner/autoencoder-meetup

Presentation about Autoencoders for Seoul AI Meetup on July 8, 2017.

Language: Jupyter Notebook - Size: 1.04 MB - Last synced at: 6 months ago - Pushed at: about 8 years ago - Stars: 0 - Forks: 1

Related Topics
interpretability 7 mechanistic-interpretability 6 machine-learning 4 sae 4 autoencoders 4 deep-learning 3 autoencoder 3 sparse-autoencoder 3 pytorch 3 python 2 convolutional-neural-networks 2 mech-interp 2 denoising-autoencoders 2 transformers 2 xai 2 tensorflow 2 neural-networks 2 jailbreak 1 breast-cancer 1 breast 1 feature-visualization 1 ai-for-science 1 computational-social-science 1 feature-dashboard 1 variational-autoencoders 1 research-tooling 1 nlp 1 wandb 1 supernodes 1 transformerlens 1 topic-modeling 1 neuron-activity 1 circuit-analysis 1 activation-functions 1 scaling-laws 1 llm-efficiency 1 prompt-probing 1 probe-prompting 1 neuronpedia 1 llm-interpretability 1 graph-analysis 1 feature-activation 1 cross-layer-transcoder 1 circuit-tracing 1 attribution-graphs 1 transcoder 1 eleutherai 1 sparse-dictionary 1 explainable-ai 1 galaxies 1 computer-visino 1 astronomy 1 saes 1 representation-engineering 1 language-model 1 yue 1 rave 1 musicgen 1 music 1 breast-imaging 1 gemma-9b-it 1 gemma-9b 1 gemma-2b 1 matlab 1 emd 1 dnn 1 bearing-fault-diagnosis 1 fashion-mnist 1 autoencoders-fashionmnist 1 autoencoder-segmentation 1 autoencoder-pytorch 1 autoencoder-mnist 1 autoencoder-classification 1 weight-decay-autoencoder 1 regularization-autoencoders 1 python3 1 neural-network 1 deeplearning 1 deep-neural-networks 1 deep-learning-algorithms 1 contractive-autonencoders 1 cnn-keras 1 ai-safety 1 eccv2024 1 concept-extraction 1 concept-bottleneck-models 1 evolutionary-algorithms 1 mixture-of-experts 1 large-language-models 1 iclr2025 1 iclr 1 hyperspectral-images 1 band-selection 1 1d-operational-layers 1 backpropagation 1 unsupervised-learning 1 taught-learning 1 supervised-neural-network 1 exercise 1 variational-autoencoder 1