I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper
•
2503.18878
•
Published
•
99
Elizaveta Goncharova
Elizaveta
AI & ML interests
None yet
Recent Activity
authored
a paper
3 days ago
When Less is Enough: Adaptive Token Reduction for Efficient Image
Representation
upvoted
a
paper
3 days ago
When Less is Enough: Adaptive Token Reduction for Efficient Image
Representation
Organizations
None yet
Elizaveta's activity
upvoted
a
paper
1 day ago
authored
a
paper
3 days ago
upvoted
a
paper
3 days ago
commented
a
paper
3 days ago
upvoted
a
paper
14 days ago
upvoted
a
paper
16 days ago
upvoted
a
paper
28 days ago
authored
a
paper
about 1 month ago
upvoted
4
papers
about 1 month ago
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
Paper
•
2502.15007
•
Published
•
168
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper
•
2502.14786
•
Published
•
138
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Paper
•
2502.14499
•
Published
•
187
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
Paper
•
2502.14502
•
Published
•
88
updated
2
collections
2 months ago
upvoted
3
papers
7 months ago
Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing
Paper
•
2409.01322
•
Published
•
96
Building and better understanding vision-language models: insights and future directions
Paper
•
2408.12637
•
Published
•
127
The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design
Paper
•
2408.12503
•
Published
•
24
upvoted
2
papers
9 months ago