Luke Marks

~Luke_Marks2

3

论文总数

1.5

年均投稿

4.1

平均评分

接收情况1/3

会议分布

ICLR

2

NeurIPS

1

发表论文 (3 篇)

20251 篇

Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders

ICLR 2025Rejected

20242 篇

Interpreting Learned Feedback Patterns in Large Language Models

NeurIPS 2024Poster

Interpreting Reward Models in RLHF-Tuned Language Models Using Sparse Autoencoders

ICLR 2024withdrawn

合作者 (8)

Fazl Barez3 篇

Amir Abdullah2 篇

Philip Torr2 篇

Rauno Arike2 篇

David Krueger2 篇

Luna Mendez1 篇

Alasdair Paren1 篇

Clement Neo1 篇