electrostatickid
/

gpt2-steering-denoiser

interpretability

activation-steering

sparse-autoencoder

Model card Files Files and versions

gpt2-steering-denoiser

Commit History

Upload denoiser.py with huggingface_hub

c40763d
verified

electrostatickid commited on 10 days ago

Upload denoiser_L8.pt with huggingface_hub

72552bf
verified

electrostatickid commited on 10 days ago

Upload denoiser.pt with huggingface_hub

b4ec1a2
verified

electrostatickid commited on 10 days ago

Upload README.md with huggingface_hub

f2ad181
verified

electrostatickid commited on 10 days ago

initial commit

1a6092f
verified

electrostatickid commited on 10 days ago