Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Nicholas Goldowsky-Dill
Observed names:
Goldowsky-Dill, Nicholas,
Nicholas W. Goldowsky-Dill
Institution:
OpenAI (United States)
Observed institutions:
Cornell University,
OpenAI (United States)
OpenAlex ID:
A5026166476
Open Problems in Mechanistic Interpretability
2025
·
Sharkey, Lee
, Chughtai, Bilal
, et al.
·
Transactions on machine learning research
·
380
Localizing Model Behavior with Path Patching
2023
·
Goldowsky-Dill, Nicholas
, MacLeod, Chris
, et al.
·
arXiv (Cornell University)
·
252
PDF
Stress Testing Deliberative Alignment for Anti-Scheming Training
2025
·
Schoen, Bronson
, Nitishinskaya, Evgenia
, et al.
·
arXiv (Cornell University)
·
153
PDF
Detecting Strategic Deception Using Linear Probes
2025
·
Goldowsky-Dill, Nicholas
, Chughtai, Bilal
, et al.
·
arXiv (Cornell University)
·
106
PDF
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
2024
·
Dan Braun
, Jordan Taylor
, et al.
·
neural information processing systems
·
85
PDF
Towards evaluations-based safety cases for AI scheming
2024
·
Balesni, Mikita
, Hobbhahn, Marius
, et al.
·
arXiv (Cornell University)
·
76
PDF
Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
2024
·
Bushnaq, Lucius
, Mendel, Jake
, et al.
·
arXiv (Cornell University)
·
18
PDF
Connecting experts in the agricultural and meteorological sciences to advance knowledge of pest management in a changing climate
2019
·
Stephen L. Young
, Nicholas W. Goldowsky-Dill
, et al.
·
The Science of The Total Environment
·
12
PDF
The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks
2024
·
Bushnaq, Lucius
, Heimersheim, Stefan
, et al.
·
arXiv (Cornell University)
·
10
PDF
Show more works
View as search
Works count:
9
Citation count:
1,091
H-index:
9
I10-index:
9
Year
Topic
Type