I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper
•
2503.18878
•
Published
•
119
•
2
Alexey Dontsov
therem
AnniBorri's profile picture
b082f689-ebc3-413d-b1f2-27bd1e86dca7's profile picture
chameleon-lizard's profile picture
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 days ago
Listener-Rewarded Thinking in VLMs for Image Preferences
upvoted
a
paper
7 days ago
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency
Models
upvoted
a
paper
16 days ago
DreamBoothDPO: Improving Personalized Generation using Direct Preference
Optimization
Organizations
commented
a
paper
3 months ago
Bug for idk data loader (code in github)
1
#4 opened 7 months ago
by
Z1zs
Will the weight of the model after unlearn be disclosed in the future?
2
#3 opened 8 months ago
by
tian9
References about the method "Twins"
2
#2 opened 8 months ago
by
Z1zs