Hugging Face's logo

Prisma-Multimodal
/
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-0-hook_mlp_out-l1-1e-05

Feature Extraction
Transformers
English
torch
clip
vision
interpretability
sparse autoencoder
sae
mechanistic interpretability
Model card Files Community
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-0-hook_mlp_out-l1-1e-05
File size: 134 Bytes 
06334fc
 
 
 
1
2
3
4
 
version https://git-lfs.github.com/spec/v1
oid sha256:87cdc788a49ecb89b7f0b62302ff4b1bf9944cd84016578d2686b3f40012e03f
size 302191832