Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-7-hook_resid_post-l1-1e-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
4bda95d
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-7-hook_resid_post-l1-1e-05
1 contributor
History:
4 commits
soniajoseph
Update README.md
4bda95d
verified
14 days ago
.gitattributes
1.52 kB
initial commit
14 days ago
README.md
1.74 kB
Update README.md
14 days ago
config.json
2.25 kB
Upload config
14 days 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
14 days ago