I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper
•
2503.18878
•
Published
•
86
Alexander Korotin
akorotin
AI & ML interests
generative modeling, Schrodinger bridges, optimal transport, diffusion models, unpaired learning
Recent Activity
upvoted
a
paper
about 19 hours ago
I Have Covered All the Bases Here: Interpreting Reasoning Features in
Large Language Models via Sparse Autoencoders
upvoted
a
paper
2 days ago
When Less is Enough: Adaptive Token Reduction for Efficient Image
Representation
upvoted
a
paper
4 days ago
Scale-wise Distillation of Diffusion Models
Organizations
None yet