Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05
like
0
Follow
Prisma
7
Feature Extraction
Transformers
English
torch
clip
vision
interpretability
sparse autoencoder
sae
mechanistic interpretability
arxiv:
2504.19475
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
main
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05
Commit History
Update README.md
1e0dcc9
verified
PraneetNeuro
commited on
Jun 25
Update README.md
c3a81b0
verified
PraneetNeuro
commited on
Jun 25
Update README.md
0cf7ab1
verified
PraneetNeuro
commited on
Jun 25
Rename n_images_2600058.pt to weights.pt
b46d6e9
verified
soniajoseph
commited on
May 8
Update README.md
fb80827
verified
soniajoseph
commited on
Nov 1, 2024
Upload SAE model
c8dfc58
verified
soniajoseph
commited on
Nov 1, 2024
Upload config
6af3169
verified
soniajoseph
commited on
Nov 1, 2024
Update README.md
968f72d
verified
soniajoseph
commited on
Nov 1, 2024
Upload SAE model
8405a5f
verified
soniajoseph
commited on
Nov 1, 2024
Upload config
9c78ba5
verified
soniajoseph
commited on
Nov 1, 2024
initial commit
e9cd8a1
verified
soniajoseph
commited on
Nov 1, 2024
soniajoseph
commited on
