Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
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
Community
Use this model
PraneetNeuro
commited on
Jun 25
Commit
c3a81b0
·
verified
·
1 Parent(s):
0cf7ab1
Update README.md
Browse files
Files changed (1)
hide
show
README.md
+1
-1
README.md
CHANGED
Viewed
@@ -74,4 +74,4 @@ metrics:
74
note={Layer 10, hook_mlp_out, Run ID: asxyxqkt}
75
}
76
77
-
[
Whitepaper](
arxiv.org/abs/2504.19475
)
74
note={Layer 10, hook_mlp_out, Run ID: asxyxqkt}
75
}
76
77
+
(Whitepaper)
[arxiv.org/abs/2504.19475
]