Scholar
Adam Scherlis
Google Scholar ID: 3i50nQ0AAAAJ
Interpretability Researcher
machine learning
high-energy physics
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
421
H-index
7
i10-index
6
Publications
13
Co-authors
16
list available
Publications
3 items
Estimating the Probability of Sampling a Trained Neural Network at Random
2025
Cited
0
Refusal in LLMs is an Affine Function
arXiv.org · 2024
Cited
0
Polysemanticity and Capacity in Neural Networks
arXiv.org · 2022
Cited
23
Co-authors
9 total
Buck Shlegeris
CEO, Redwood Research
Benjamin Weinstein-Raun
Palisade Research, AI Impacts
Daniel M. Ziegler
Redwood Research
Noa Nabeshima
UC Santa Barbara
Lawrence Chan
PhD Student, UC Berkeley
Stanislav Fort
Google DeepMind
Joe Benton
Anthropic
Adam Jermyn
Flatiron Research Fellow