Scholar
Atticus Geiger
Google Scholar ID: w2Qzno8AAAAJ
Pr(Ai)²R Group
Artificial Intelligence
Natural Language
Mechanistic Interpretability
Causality
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,484
H-index
24
i10-index
28
Publications
20
Co-authors
23
list available
Contact
CV
Open ↗
GitHub
Open ↗
Publications
28 items
Language Model Activations Inhabit Privileged Error-Correcting Basins
2026
Cited
0
Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
2026
Cited
0
Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation
2026
Cited
0
Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds
2026
Cited
0
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
2026
Cited
0
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
2026
Cited
0
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
2026
Cited
0
Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
2026
Cited
0
Load more
Resume
Academic Achievements
View my publications and research projects; Citations and publication metrics on Google Scholar.
Research Experience
Currently at Goodfire researching causally grounded mechanistic interpretability for understanding and controlling AI.
Education
Has a B.S. in Symbolic Systems, an M.S. in Computer Science, and a PhD in Linguistics all from Stanford.
Background
Broadly interested in causality, cognition, language, and AI.
Miscellany
Contact me by reordering the following strings: 'ai', '@', '.', 'atticus', 'goodfire'
Co-authors
15 total
Christopher Potts
Professor of Linguistics and, by courtesy, of Computer Science
Zhengxuan Wu
Stanford University
Thomas Icard
C.I. Lewis Professor of Philosophy and Professor of Computer Science (courtesy), Stanford University
Noah D. Goodman
Stanford University
Aryaman Arora
Stanford University
Karel D'Oosterlinck
PhD student, Ghent University.
Douwe Kiela
Contextual AI, Stanford University
Neel Nanda
Mechanistic Interpretability Team Lead, Google DeepMind