Usha Bhalla
Scholar

Usha Bhalla

Google Scholar ID: 8xZrwdsAAAAJ
Ph.D. Student, Harvard University
Machine Learning Interpretability
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
143
 
H-index
5
 
i10-index
3
 
Publications
13
 
Co-authors
0
 
Contact
No contact links provided.
Publications
8 items
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
2026
Cited
0
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
2026
Cited
0
Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
2026
Cited
0
Do Sparse Autoencoders Capture Concept Manifolds?
2026
Cited
0
RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories
2025
Cited
0
Interpretability Illusions with Sparse Autoencoders: Evaluating Robustness of Concept Representations
2025
Cited
0
Building Bridges, Not Walls -- Advancing Interpretability by Unifying Feature, Data, and Model Component Attribution
2025
Cited
0
Towards Unifying Interpretability and Control: Evaluation via Intervention
arXiv.org · 2024
Cited
1
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)