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_mlp_out-l1-5e-05
like
0
Follow
Prisma
6
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
d19f127
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-5e-05
Commit History
Upload SAE model
d19f127
verified
soniajoseph
commited on
Nov 1, 2024
Upload config
cdb5b1b
verified
soniajoseph
commited on
Nov 1, 2024
initial commit
8c56cde
verified
soniajoseph
commited on
Nov 1, 2024
