Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
免费去水印
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
xet
Community
Use this model
main
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05
302 MB
2 contributors
History:
11 commits
PraneetNeuro
Update README.md
1e0dcc9
verified
6 months ago
.gitattributes
1.52 kB
initial commit
about 1 year ago
README.md
1.71 kB
Update README.md
6 months ago
config.json
2.25 kB
Upload config
about 1 year ago
weights.pt
302 MB
xet
Rename n_images_2600058.pt to weights.pt
7 months ago