Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-8-hook_resid_post-l1-5e-05
like
0
Follow
Prisma
5
Feature Extraction
Transformers
English
torch
clip
vision
interpretability
sparse autoencoder
sae
mechanistic interpretability
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
8dd5861
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-8-hook_resid_post-l1-5e-05
Commit History
Upload SAE model
8dd5861
verified
soniajoseph
commited on
14 days ago
Upload config
7b8f712
verified
soniajoseph
commited on
14 days ago
initial commit
0d66f19
verified
soniajoseph
commited on
14 days ago
