Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-2-hook_resid_post-l1-0.0001
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
0279103
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-2-hook_resid_post-l1-0.0001
302 MB
1 contributor
History:
3 commits
soniajoseph
Upload SAE model
0279103
verified
11 months ago
.gitattributes
Safe
1.52 kB
initial commit
11 months ago
config.json
2.25 kB
Upload config
11 months ago
n_images_2600058.pt
302 MB
xet
Upload SAE model
11 months ago
