Paper
Hub
搜索
Toggle language
Adam Karvonen
~Adam_Karvonen1
4
论文总数
2.0
年均投稿
6.8
平均评分
接收情况
4
/
4
会议分布
ICML
2
NeurIPS
1
COLM
1
发表论文 (4 篇)
2025
2 篇
5.5
4
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
ICML 2025
Poster
8.3
4
Learning Multi-Level Features with Matryoshka Sparse Autoencoders
ICML 2025
Poster
2024
2 篇
6.3
3
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
NeurIPS 2024
Poster
7.0
4
Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
COLM 2024
Poster
合作者 (20)
NN
Neel Nanda
2 篇
CR
Can Rager
2 篇
SM
Samuel Marks
2 篇
BB
Bart Bussmann
1 篇
NN
Noa Nabeshima
1 篇
AC
Arthur Conmy
1 篇
CM
Callum Stuart McDougall
1 篇
CT
Curt Tigges
1 篇
查看全部 20 位合作者