Cite
Notes
Only stored in your browser.
Attribution
Training Language Models to Explain Their Own Computations
arXiv 2025
Universal Neurons in GPT2 Language Models
arXiv 2024
Opening the AI black box: program synthesis via mechanistic interpretability
Algorithmic progress in language models
from 4 papers
Tara Rezaei Kheirkhah
Anish Mudide
Anson Ho
researcher
Belinda Z. Li
Chloe Loughridge
David Atkinson
David Owen
Dimitris Bertsimas
Ege Erdil
Eric J. Michaud