activity
20222026
most citedAuditing language models for hidden objectives

3 citations · 6 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025

Who's the Evil Twin? Differential Auditing for Undesired Behavior

Ishwar Balappanawar, Venkata Hasith Vattikuti, Greta Kintzley +2

Detecting hidden behaviors in neural networks poses a significant challenge due to minimal prior knowledge and potential adversarial obfuscation. We explore this problem by framing…

cs.LG2025

Studying Cross-cluster Modularity in Neural Networks

Satvik Golechha, Maheep Chaudhary, Joan Velja +2

An approach to improve neural network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We define a measure…

cs.LG2024

Training Neural Networks for Modularity aids Interpretability

Satvik Golechha, Dylan Cope, Nandi Schoots

An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models t…

cs.LG2024

Progress Measures for Grokking on Real-world Tasks

Satvik Golechha

Grokking, a phenomenon where machine learning models generalize long after overfitting, has been primarily observed and studied in algorithmic tasks. This paper explores grokking i…

cs.LG2024

Challenges in Mechanistically Interpreting Model Representations

Satvik Golechha, James Dao

Mechanistic interpretability (MI) aims to understand AI models by reverse-engineering the exact algorithms neural networks learn. Most works in MI so far have studied behaviors and…

cs.LG20223 cited

Predicting Treatment Adherence of Tuberculosis Patients at Scale

Mihir Kulkarni, Satvik Golechha, Rishi Raj +9

Tuberculosis (TB), an infectious bacterial disease, is a significant cause of death, especially in low-income countries, with an estimated ten million new cases reported globally i…