Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
SoraWatermarkRemover
Log In
Sign Up
Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-5-hook_resid_post-l1-5e-05
like
0
Follow
Prisma
7
Feature Extraction
Transformers
English
torch
clip
vision
interpretability
sparse autoencoder
sae
mechanistic interpretability
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
5b2ea0d
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-5-hook_resid_post-l1-5e-05
302 MB
1 contributor
History:
4 commits
soniajoseph
Update README.md
5b2ea0d
verified
12 months ago
.gitattributes
Safe
1.52 kB
initial commit
12 months ago
README.md
1.73 kB
Update README.md
12 months ago
config.json
Safe
2.25 kB
Upload config
12 months ago
n_images_2600058.pt
Safe
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
302 MB
xet
Upload SAE model
12 months ago