Hugging Face
Models
Datasets
Spaces
Buckets
new
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
ARotting
/
snip-scope-sae
like
0
mechanistic-interpretability
sparse-autoencoder
language-model
feature-discovery
gradio
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
snip-scope-sae
/
source
11 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
ARotting
Publish Top-k sparse autoencoder for SNIP hidden activations
82138fc
verified
2 days ago
app.py
Safe
1.81 kB
Publish Top-k sparse autoencoder for SNIP hidden activations
2 days ago
model.py
Safe
1.4 kB
Publish Top-k sparse autoencoder for SNIP hidden activations
2 days ago
requirements.txt
Safe
160 Bytes
Publish Top-k sparse autoencoder for SNIP hidden activations
2 days ago
train.py
Safe
7.59 kB
Publish Top-k sparse autoencoder for SNIP hidden activations
2 days ago
