Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
LuckerZ
/
moground-saes
Like
1
sparse-autoencoder
interpretability
vision-language
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
moground-saes
4.3 GB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
LuckerZ
Vision-language Top-K SAEs for Qwen2.5-VL-3B and LLaVA-NeXT-8B
b8c93e9
verified
11 days ago
__pycache__
Vision-language Top-K SAEs for Qwen2.5-VL-3B and LLaVA-NeXT-8B
11 days ago
llavanext
Vision-language Top-K SAEs for Qwen2.5-VL-3B and LLaVA-NeXT-8B
11 days ago
qwen
Vision-language Top-K SAEs for Qwen2.5-VL-3B and LLaVA-NeXT-8B
11 days ago
.gitattributes
Safe
1.52 kB
initial commit
11 days ago
MANIFEST.json
2.59 kB
Vision-language Top-K SAEs for Qwen2.5-VL-3B and LLaVA-NeXT-8B
11 days ago
README.md
2.85 kB
Vision-language Top-K SAEs for Qwen2.5-VL-3B and LLaVA-NeXT-8B
11 days ago
load_sae.py
1.38 kB
Vision-language Top-K SAEs for Qwen2.5-VL-3B and LLaVA-NeXT-8B
11 days ago
