sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05

Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05

EmbeddingstorchLicense: apache-2.0
Tracked by OpenModelStats since August 25, 2026View on Hugging Face ↗
Downloads 30D
172
Total downloads
3,758
Gained 7D
Gained 30D
Likes
0
Rank · tracked models
this week
Parameters
Last source update
Jun 25, 2025

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-25. Charts appear as daily observations accumulate.

Overview

sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05 is a embeddings model published by Prisma-Multimodal. OpenModelStats has tracked the model since Aug 25, 2026, most recently observing it 20h ago.

Published
Nov 1, 2024
Last updated
Jun 25, 2025
Library
torch
License
apache-2.0
Task
Embeddings
Parameters
Spaces
0
Derivative models
Velocity 7D/day
torchclipvisiontransformersinterpretabilitysparse autoencodersaemechanistic interpretabilityfeature-extractionenarxiv:2504.19475license:apache-2.0

Similar models

Models similar to sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05
ModelDL 30D
bge-small-en-v1.5BAAI66.4M
bge-large-en-v1.5BAAI13M
bge-base-en-v1.5BAAI11.5M
multilingual-e5-largeintfloat6.9M
Qwen3-Embedding-0.6BQwen6.6M
granite-embedding-small-english-r2ibm-granite5.1M