Tom Lieberum

~Tom_Lieberum2

2

论文总数

1.0

年均投稿

5.4

平均评分

接收情况1/2

会议分布

ICLR

1

NeurIPS

1

发表论文 (2 篇)

20251 篇

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

ICLR 2025Rejected

20241 篇

Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders

NeurIPS 2024Poster

合作者 (8)

Arthur Conmy2 篇

Janos Kramar2 篇

Neel Nanda2 篇

Senthooran Rajamanoharan2 篇

Vikrant Varma2 篇

Nicolas Sonnerat1 篇

Lewis Smith1 篇

Rohin Shah1 篇