Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Hanish
/
sparse-steer-gpt1
Like
0
Text Generation
Safetensors
English
steering-vectors
activation-steering
sparse-steering
one-bit
interpretability
mechanistic-interpretability
representation-engineering
contrastive-activation-addition
gpt-1
openai-gpt
sparse
model-steering
residual-stream
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
sparse-steer-gpt1
/
figures
552 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
Hanish
Add paper figures
9568262
verified
about 2 months ago
fig1_contrast_by_layer.png
Safe
43.3 kB
Add paper figures
about 2 months ago
fig2_layer_strength.png
128 kB
xet
Add paper figures
about 2 months ago
fig3_sparsity.png
186 kB
xet
Add paper figures
about 2 months ago
fig4_concentration.png
116 kB
xet
Add paper figures
about 2 months ago
fig5_cosine.png
Safe
78.4 kB
Add paper figures
about 2 months ago