Janos Kramar

~Janos_Kramar1

4

论文总数

2.0

年均投稿

5.4

平均评分

接收情况2/4

会议分布

NeurIPS

2

ICLR

2

发表论文 (4 篇)

20251 篇

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

ICLR 2025Rejected

20243 篇

On scalable oversight with weak LLMs judging strong LLMs

NeurIPS 2024Poster

Explaining grokking through circuit efficiency

ICLR 2024Rejected

Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders

NeurIPS 2024Poster

合作者 (18)

Rohin Shah3 篇

Vikrant Varma3 篇

Zachary Kenton2 篇

Arthur Conmy2 篇

Neel Nanda2 篇

Senthooran Rajamanoharan2 篇

Tom Lieberum2 篇

Ramana Kumar1 篇