Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-5-hook_mlp_out-l1-8e-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
da7d325
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-5-hook_mlp_out-l1-8e-05
1 contributor
History:
3 commits
soniajoseph
Upload SAE model
da7d325
verified
2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
config.json
Safe
2.25 kB
Upload config
2 months ago
n_images_2600058.pt
302 MB
LFS
Upload SAE model
2 months ago
