mwatkins1970 / SAE_Feature_Interpretability_Tool

A tool to assist in the interpretation of learned features in sparse autoencoders (in particular the four SAE's trained by Joseph Bloom on Gemma-2B).
18Updated 4 months ago

Alternatives and similar repositories for SAE_Feature_Interpretability_Tool:

Users that are interested in SAE_Feature_Interpretability_Tool are comparing it to the libraries listed below