Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Wes Gurnee
Observed name:
Gurnee, Wes
Institutions:
Anthropic (United States),
Massachusetts Institute of Technology
Observed institutions:
University of Cambridge,
Anthropic (United States),
Massachusetts Institute of Technology
ORCID:
0000-0002-0752-3934
Observed ORCID:
0000-0002-0752-3934
OpenAlex ID:
A5036313350
Refusal in Language Models Is Mediated by a Single Direction
2024
·
Andy Arditi
, Oscar Obeso
, et al.
·
neural information processing systems
·
66
Learning sparse nonlinear dynamics via mixed-integer optimization
2023
·
Dimitris Bertsimas
, Wes Gurnee
·
Nonlinear Dynamics
·
54
PDF
Language Models Represent Space and Time
2023
·
Gurnee, Wes
, Tegmark, Max
·
arXiv (Cornell University)
·
46
PDF
Fairmandering: A column generation heuristic for fairness-optimized political districting
2021
·
Wes Gurnee
, David B. Shmoys
·
Society for Industrial and Applied Mathematics eBooks
·
20
PDF
Finding Neurons in a Haystack: Case Studies with Sparse Probing
2023
·
Gurnee, Wes
, Nanda, Neel
, et al.
·
arXiv (Cornell University)
·
15
PDF
External Invariants: A Cryptographic Trust Architecture for Institutional AI Inference
2024
·
Arditi, Andy
, Obeso, Oscar
, et al.
·
arXiv (Cornell University)
·
9
PDF
Combatting Gerrymandering with Social Choice
2022
·
Nikhil Garg
, Wes Gurnee
, et al.
·
ACM Conference on Economics and Computation (EC)
·
5
Emotion Concepts and their Function in a Large Language Model
2026
·
Sofroniew, Nicholas
, Kauvar, Isaac
, et al.
·
arXiv (Cornell University)
·
4
Not All Language Model Features Are One-Dimensionally Linear
2024
·
Engels, Joshua
, Michaud, Eric J.
, et al.
·
arXiv (Cornell University)
·
4
PDF
Combatting Gerrymandering with Ranked Choice Voting: An Experimental Analysis of Multi-member Districts in the United States
2021
·
Garg, Nikhil
, Gurnee, Wes
, et al.
·
arXiv (Cornell University)
·
3
PDF
Combating Gerrymandering with Ranked Choice Voting: An Experimental Analysis of Multimember Districts in the United States
2026
·
Nikhil Garg
, Wes Gurnee
, et al.
·
Operations Research
·
2
Universal Neurons in GPT2 Language Models
2024
·
Gurnee, Wes
, Horsley, Theo
, et al.
·
arXiv (Cornell University)
·
2
PDF
Confidence Regulation Neurons in Language Models
2024
·
Alessandro Stolfo
, Ben Wu
, et al.
·
neural information processing systems
·
2
PDF
The Injected Word Reaches the Answer but Not the Report: Injected-Thought Reports in Qwen3 Run Mainly Through a Content-Free Yes Direction
2026
·
Gurnee, Wes
, Sofroniew, Nicholas
, et al.
·
arXiv (Cornell University)
·
1
PDF
Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience
2024
·
He, Zhonghao
, Achterberg, Jascha
, et al.
·
arXiv (Cornell University)
·
1
PDF
A Shared Subcircuit Lets LLMs Count Down Across Tasks
2026
·
Dunefsky, Jacob
, Gurnee, Wes
, et al.
·
arXiv (Cornell University)
PDF
When Models Manipulate Manifolds: The Geometry of a Counting Task
2026
·
Gurnee, Wes
, Ameisen, Emmanuel
, et al.
·
arXiv (Cornell University)
PDF
Emotion Concepts and their Function in a Large Language Model
2026
·
Sofroniew, Nicholas
, Kauvar, Isaac
, et al.
·
arXiv (Cornell University)
PDF
Remarkable Robustness of LLMs: Stages of Inference?
2025
·
Vedang Lad
, Jin Hwa Lee
, et al.
·
neural information processing systems
PDF
OpenWebTextCorpus
2024
·
Gurnee, Wes
·
TIB Data Manager
Training Dynamics of Contextual N-Grams in Language Models
2023
·
Quirke, Lucia
, Heindrich, Lovis
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
21
Citation count:
233
H-index:
6
I10-index:
5
Year
Topic
Type
