ICA Lens: Interpreting Language Models Without Training Another Dictionary

arXiv:2606.11722v1 Announce Type: cross Abstract: Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (SAEs) have become the standard tool for this purpose, but using them as the default first lens often requires training, storing, and evaluating...

Läs hela artikeln hos källan.