search

OpenMOSS / Language-Model-SAEs

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
32 stars 6 forks source link

feat(analysis): accelerate analysis with chunked d_sae and stop_at_la… #7

Closed Hzfinfdu closed 3 months ago

Hzfinfdu commented 3 months ago

…yer and a pre-check before sorting