AgoraResearch hub
ExploreLibraryProfile
Account
Sign In
Suraj Srinivas
Scholar

Suraj Srinivas

Google Scholar ID: J2JWgKgAAAAJ
Research Scientist at Bosch
Deep LearningMachine Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
2,377
 
H-index
17
 
i10-index
18
 
Publications
20
 
Co-authors
16
list available
Contact
No contact links provided.
Publications
5 items
Interpretability Illusions with Sparse Autoencoders: Evaluating Robustness of Concept Representations
2025
Cited
0
Towards Interpretable Soft Prompts
2025
Cited
0
Towards Unifying Interpretability and Control: Evaluation via Intervention
arXiv.org · 2024
Cited
1
How much can we forget about Data Contamination?
arXiv.org · 2024
Cited
1
Certifying LLM Safety against Adversarial Prompting
arXiv.org · 2023
Cited
124
Resume (English only)
Co-authors
16 total
R. Venkatesh Babu
R. Venkatesh Babu
CDS, Indian Institute of Science, Bangalore, India
Himabindu Lakkaraju
Himabindu Lakkaraju
Assistant Professor, Harvard University; Senior Staff Research Scientist, Google.
François Fleuret
François Fleuret
University of Geneva
Co-author 4
Co-author 4
Usha Bhalla
Usha Bhalla
Ph.D. Student, Harvard University
Tessa Han
Tessa Han
Harvard University
Aounon Kumar
Aounon Kumar
Research Associate, Harvard University
Alex Oesterling
Alex Oesterling
PhD Candidate, Harvard University