GitHub / explanare / eval-neuron-explanation

A framework for evaluating auto-interp pipelines, i.e., natural language explanations of neurons.

JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explanare%2Feval-neuron-explanation
PURL: pkg:github/explanare/eval-neuron-explanation

Stars: 2
Forks: 0
Open issues: 0

License: None
Language: Python
Size: 495 KB
Dependencies parsed at: Pending

Created at: almost 2 years ago
Updated at: 10 months ago
Pushed at: about 1 year ago
Last synced at: 6 months ago

Topics: causal-intervention, explanability, interpretability, neurons, probing

Loading...