Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-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
486e5b8
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_resid_post-l1-0.0001
1 contributor
History:
6 commits
soniajoseph
Upload SAE model
486e5b8
verified
about 1 month ago
.gitattributes
1.52 kB
initial commit
about 1 month ago
README.md
1.74 kB
Update README.md
about 1 month ago
config.json
2.26 kB
Upload config
about 1 month ago
n_images_2600058.pt
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
What is a pickle import?
302 MB
LFS
Upload SAE model
about 1 month ago