Aleksandar Makelov

~Aleksandar_Makelov1

2

论文总数

1.0

年均投稿

6.7

平均评分

接收情况2/2

会议分布

ICLR

2

发表论文 (2 篇)

20251 篇

Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

ICLR 2025Poster

20241 篇

Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching

ICLR 2024Poster

合作者 (3)

Georg Lange2 篇

Neel Nanda2 篇

Atticus Geiger1 篇