Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-0-hook_resid_post-l1-0.0001
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
5a7472a
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-0-hook_resid_post-l1-0.0001
Commit History
Upload SAE model
5a7472a
verified
soniajoseph
commited on
13 days ago
Upload config
16e663b
verified
soniajoseph
commited on
13 days ago
initial commit
4b3e110
verified
soniajoseph
commited on
13 days ago