Accessibility settings

This paper is in the following e-collection/theme issue:

Viewpoints and Perspectives in AI (22) Generative Language Models Including ChatGPT (893) AI Language Models in Health Care (292) Applications of AI (388)

Published on in Vol 5 (2026)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/81134, first published .
Doctors analyze SAE interpretability dashboard with AI model data

Application of Sparse Autoencoders to Enhance Mechanistic Interpretability of Large Language Models in Medicine

Application of Sparse Autoencoders to Enhance Mechanistic Interpretability of Large Language Models in Medicine

Authors of this article:

Andre Metzger1 Author Orcid Image ;   Shiv Patil1 Author Orcid Image ;   Lauren R Sugarmann2 Author Orcid Image ;   Mert Karabacak1 Author Orcid Image ;   Konstantinos Margetis1 Author Orcid Image
Article Authors Cited by Tweetations Metrics

Andre Metzger   1 * , BA ;   Shiv Patil   1 * , MS ;   Lauren R Sugarmann   2 , BSc ;   Mert Karabacak   1 , MD ;   Konstantinos Margetis   1 , MD, PhD

1 Mount Sinai Health System, New York, NY, United States

2 Department of Neurosurgery, The Warren Alpert Medical School of Brown University, Providence, RI, United States

*these authors contributed equally

Corresponding Author: