影响力指数

28.32/100

前 26.4%

全站排名 #17,002

发表论文4 篇

平均评分4.9

年均产出2.0 篇/年

Daniil Laptev

MS student@Kuban State University·俄罗斯·OpenReview

研究方向

mechanistic interpretability · sparse autoencoders · deep learning

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders

ICLR 2026Rejected

Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors

ICLR 2026Rejected

Teach Old SAEs New Domain Tricks with Boosting

COLM 2025Poster

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

ICML 2025Poster

合作者 (9)

Daniil Gavrilov

Nikita Balagansky

Yaroslav Aksenov

Vadim Kurochkin

Nikita Koriagin

Alexey Gorbatovski

Boris Shaposhnikov