Sparse Autoencoders
Collection
SAEs are tools for understanding the internal representations of neural networks. These can be loaded using https://github.com/EleutherAI/sae
•
9 items
•
Updated
•
2
Emil Fagerholm PRO
eMILF2
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
19 days ago
Sparse Autoencoders
liked
a model
19 days ago
EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k
liked
a Space
about 1 month ago
openfree/PDF-RAG
Organizations
None yet