Picture for Satvik Golechha

Satvik Golechha

Auditing language models for hidden objectives

Add code
Mar 14, 2025
Viaarxiv icon

Modular Training of Neural Networks aids Interpretability

Add code
Feb 04, 2025
Figure 1 for Modular Training of Neural Networks aids Interpretability
Figure 2 for Modular Training of Neural Networks aids Interpretability
Figure 3 for Modular Training of Neural Networks aids Interpretability
Figure 4 for Modular Training of Neural Networks aids Interpretability
Viaarxiv icon

Progress Measures for Grokking on Real-world Datasets

Add code
May 21, 2024
Viaarxiv icon

NICE: To Optimize In-Context Examples or Not?

Add code
Feb 16, 2024
Viaarxiv icon

CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients

Add code
Feb 07, 2024
Viaarxiv icon

Position Paper: Toward New Frameworks for Studying Model Representations

Add code
Feb 06, 2024
Viaarxiv icon

Predicting Treatment Adherence of Tuberculosis Patients at Scale

Add code
Nov 15, 2022
Figure 1 for Predicting Treatment Adherence of Tuberculosis Patients at Scale
Figure 2 for Predicting Treatment Adherence of Tuberculosis Patients at Scale
Figure 3 for Predicting Treatment Adherence of Tuberculosis Patients at Scale
Figure 4 for Predicting Treatment Adherence of Tuberculosis Patients at Scale
Viaarxiv icon