andyx10/dit-loras-interpreting download history

andyx10/dit-loras-interpreting is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,692 times (345 in the last 7 days), and 1,692 times in total. It ranks #12,935 among datasets by monthly downloads.

andyx10/dit-loras-interpreting Experimenting with interpreting write vectors over 100 hidden-topic model organisms fromdiff-interpretation-tuning/loras implementation We use 'self_attn.o_proj andmlp.down_proj` for write vectors: two per block across 36 blocks, with a to

Open andyx10/dit-loras-interpreting on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.