Nora Belrose
Scholar

Nora Belrose

Google Scholar ID: p_oBc64AAAAJ
Research Lead, EleutherAI
interpretabilityneural networkstransformersnlpai
Google Scholar↗
Citations & Impact
All-time
Citations
701
 
H-index
10
 
i10-index
10
 
Publications
20
 
Co-authors
14
list available
Contact
No contact links provided.
Publications
14 items
Binary Sparse Coding for Interpretability
2025
Cited
0
Evaluating SAE interpretability without explanations
2025
Cited
0
Mechanistic Anomaly Detection for"Quirky"Language Models
2025
Cited
0
Slowing Learning by Erasing Simple Features
2025
Cited
0
Examining Two Hop Reasoning Through Information Content Scaling
2025
Cited
0
Converting MLPs into Polynomials in Closed Form
2025
Cited
0
Partially Rewriting a Transformer in Natural Language
2025
Cited
0
Estimating the Probability of Sampling a Trained Neural Network at Random
2025
Cited
0
Resume (English only)
Co-authors
14 total
Stella Biderman
Stella Biderman
EleutherAI
Co-author 2
Co-author 2
Adam Gleave
Adam Gleave
CEO at FAR AI
Zach Furman
Zach Furman
Research Fellow, Timaeus
Co-author 5
Co-author 5
Lev McKinney
Lev McKinney
University of Toronto
Jacob Steinhardt
Jacob Steinhardt
Stanford University
Sergey Levine
Sergey Levine
UC Berkeley, Physical Intelligence