Lee Sharkey

~Lee_Sharkey1

4

论文总数

2.0

年均投稿

6.2

平均评分

接收情况4/4

会议分布

ICLR

3

NeurIPS

1

发表论文 (4 篇)

20252 篇

Bilinear MLPs enable weight-based mechanistic interpretability

ICLR 2025Spotlight

Sparse Autoencoders Do Not Find Canonical Units of Analysis

ICLR 2025Poster

20242 篇

Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

NeurIPS 2024Poster

Sparse Autoencoders Find Highly Interpretable Features in Language Models

ICLR 2024Poster

合作者 (17)

Michael T Pearce2 篇

Jordan Taylor1 篇

Nicholas Goldowsky-Dill1 篇

Bart Bussmann1 篇

Curt Tigges1 篇

Joseph Isaac Bloom1 篇

Neel Nanda1 篇