Paper
Hub
搜索
Toggle language
Wes Gurnee
~Wes_Gurnee1
5
论文总数
2.5
年均投稿
6.7
平均评分
接收情况
5
/
5
会议分布
NeurIPS
3
ICLR
2
发表论文 (5 篇)
2025
2 篇
6.4
5
Remarkable Robustness of LLMs: Stages of Inference?
NeurIPS 2025
Poster
7.0
4
Not All Language Model Features Are One-Dimensionally Linear
ICLR 2025
Poster
2024
3 篇
6.8
4
Language Models Represent Space and Time
ICLR 2024
Poster
7.0
4
Confidence Regulation Neurons in Language Models
NeurIPS 2024
Poster
6.5
4
Refusal in Language Models Is Mediated by a Single Direction
NeurIPS 2024
Poster
合作者 (17)
MT
Max Tegmark
3 篇
NN
Neel Nanda
2 篇
AS
Alessandro Stolfo
1 篇
BW
Ben Peng Wu
1 篇
MS
Mrinmaya Sachan
1 篇
XS
Xingyi Song
1 篇
YB
Yonatan Belinkov
1 篇
EM
Eric J Michaud
1 篇
查看全部 17 位合作者