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

UNSTRUCTURED Large language models (LLM) are positioned to transform the practice of medicine through their ability to determine clinical diagnoses, form treatment plans, and optimize medical workflows. Understanding the internal mechanism by which these models operate is necessary to legitimize LLMs in clinical practice. This field of research is called mechanistic interpretability. By extracting human-interpretable features from LLMs, sparse autoencoders (SAEs) represent a promising development in the field of digital medicine.