Asma Ghandeharioun

Research Scientist, Google DeepMind

Joined

June 2017

Names

Asma Ghandeharioun

Emails

****@mit.edu (Confirmed)

****@google.com (Confirmed)

Personal Links

Career & Education History

Research Scientist

Google DeepMind (google.com)

2024 – Present

Research Scientist

Google (google.com)

2021 – 2024

PhD student

Massachusetts Institute of Technology (mit.edu)

2016 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

ML interpretability

Present

deep learning

Present

AI safety

Present

Publications

Think Before You Lie: How Reasoning Leads to Honesty
Katja Filippova, Ann Yuan, Asma Ghandeharioun, Carter Blum, Alicia Machado, Jessica Hoffmann, Daphne Ippolito, Martin Wattenberg, Lucas Dixon
- OpenReview Archive Direct Upload
- Readers: Everyone
Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics
Carter Blum, Katja Filippova, Ann Yuan, Asma Ghandeharioun, Julian Zimmert, Fred Zhang, Jessica Hoffmann, Tal Linzen, Martin Wattenberg, Lucas Dixon, Mor Geva
- Submitted to ICLR 2026
- Readers: Everyone
Towards Unifying Interpretability and Control: Evaluation via Intervention
Usha Bhalla, Suraj Srinivas, Asma Ghandeharioun, Himabindu Lakkaraju
- Submitted to ICLR 2025
- Readers: Everyone
When Can Transformers Count to n?
Gilad Yehudai, Haim Kaplan, Asma Ghandeharioun, Mor Geva, Amir Globerson
- Submitted to ICLR 2025
- Readers: Everyone
Who's asking? User personas and the mechanics of latent misalignment
Asma Ghandeharioun, Ann Yuan, Marius Guerard, Emily Reif, Michael A. Lepori, Lucas Dixon
- NeurIPS 2024 spotlight
- Readers: Everyone
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, Mor Geva
- ICML 2024 Poster
- Readers: Everyone
Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman, Andrew Kyle Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun
- ICML 2024 Poster
- Readers: Everyone
Comparing Representational and Functional Similarity in Small Transformer Language Models
Dan Friedman, Andrew Kyle Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun
- UniReps Poster
- Readers: Everyone
Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman, Andrew Kyle Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun
- Submitted to ICLR 2024
- Readers: Everyone
Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Peter Hase, Mohit Bansal, Been Kim, Asma Ghandeharioun
- NeurIPS 2023 spotlight
- Readers: Everyone

View all 44 publications

Co-Authors

View all 83 co-authors