Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders
Paper
• 2410.22366 • Published
• 84
Matteo Santelmo
matsant01
AI & ML interests
LLM self-improvement, reasoning, AI4Science
Recent Activity
updated
a dataset about 7 hours ago
matsant01/blind-spots-bench liked
a model 1 day ago
allenai/Olmo-3-7B-Instruct updated
a Space about 1 month ago
matsant01/dit-editor-user-study Organizations
upvoted a paper over 1 year ago