People
People in interpretability
18 people in the USASI People directory whose profiles list interpretability as a field of their work. Listed alphabetically; this is not a ranking. Each profile covers public professional work only, cited to official pages.
Aeree Cho
Machine learning PhD student in the Polo Club of Data Science (since fall 2024), Georgia Institute of Technology
Georgia Tech machine learning PhD student and lead author of the open-source Transformer Explainer
Aleksandra Mojsilović
Head of Trustworthy Machine Intelligence and IBM Fellow (as described by IBM Research in February 2023), IBM Research
Led Trustworthy Machine Intelligence at IBM Research; co-author of AI Fairness 360, AIX360 and FactSheets
Arthur Conmy
Member of Technical Staff, Anthropic
Anthropic Member of Technical Staff; former Google DeepMind senior research engineer; ACDC first author
Carlos Guestrin
Professor, Computer Science; Fortinet Founders Professor and Senior Fellow at the Stanford Institute for Human-Centered AI, Stanford University
Stanford computer science professor; co-author of XGBoost and LIME and co-founder of Turi
Chris Olah
Co-founder, Anthropic
Anthropic co-founder working on reverse engineering neural networks; previously led interpretability at OpenAI
David Bau
Assistant Professor of Computer Science, Northeastern University
Northeastern professor studying neural-network internals; Bau's lab launched the NDIF project
Duen Horng "Polo" Chau
Professor and Associate Chair, School of Computational Science and Engineering; Associate Director, MS in Analytics, Georgia Institute of Technology
Georgia Tech professor whose Polo Club of Data Science created Transformer Explainer and CNN Explainer
Hendrik Strobelt
Senior Research Scientist; Explainability Lead, MIT-IBM Watson AI Lab, IBM Research
Senior Research Scientist at IBM Research and MIT-IBM lab explainability lead; co-creator of GLTR
Jacob Andreas
Associate Professor, Massachusetts Institute of Technology
MIT associate professor in EECS and CSAIL studying language learning and how neural models represent meaning
Jacob Steinhardt
Associate Professor of Statistics and EECS, University of California, Berkeley
UC Berkeley associate professor of Statistics and EECS; founder and CEO of the nonprofit lab Transluce
Kenneth Li
Researcher, Thinking Machines Lab
Thinking Machines Lab researcher; lead author of Othello world-model and Inference-Time Intervention papers
Kush R. Varshney
IBM Fellow, directing Human-Centered Trustworthy AI research, IBM Research
IBM Fellow directing trustworthy AI research at IBM; team behind AI Fairness 360 and Granite Guardian
Michael Hind
Distinguished Research Staff Member, IBM Research
Distinguished Research Staff Member at IBM Research; co-author of AI Fairness 360, AIX360 and FactSheets
Neel Nanda
Runs the mechanistic interpretability team, Google DeepMind
Runs the Google DeepMind mechanistic interpretability team; creator of the TransformerLens library
Nick Frosst
Co-founder, Cohere
Co-founder of Cohere; co-author with Geoffrey Hinton of capsule-network research at Google Brain
Sameer Singh
Professor, Department of Computer Science, University of California, Irvine
UC Irvine professor of computer science; co-author of LIME and CheckList; former Ai2 Allen Fellow
Samuel Marks
Member of Technical Staff; leads the Cognitive Oversight subteam of the Alignment Science team, Anthropic
Leads the Cognitive Oversight subteam at Anthropic; first author of a study on auditing hidden objectives
Sarthak Jain
Machine learning team member, Profluent
Member of Profluent's machine learning team and first author of the Profluent-E1 protein encoder models
Support Us
Help keep USASI useful.
Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).
About supporting this project