I'm a student at Stanford University currently doing research in mechanistic interpretability. My current interest is on transformers' internal representations and reverse engineer algorithms they learned after grokking.
- United States
- linkedin.com/in/danh-h-nguyen
Pinned Loading
-
Discrete-Log-Clock
Discrete-Log-Clock PublicReverse-engineered how transformer do modular multiplication. Accepted at ICML 2026 Mechanistic Interpretability Workshop.
Jupyter Notebook
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.

