Survival of the Fittest Representation: A Case Study with Modular Addition
_{Xiaoman Delores Ding*, Zifan Carl Guo*, Eric J. Michaud, Ziming Liu, Max Tegmark. In Mechanistic Interpretability Workshop at the ICML 2024. [arXiv][Twitter][Code]}

Universal Neurons in GPT2 Language Models
_{Wes Gurnee, Theo Horsley, Zifan Carl Guo, Tara Rezaei Kheirkhah, Qinyi Sun, Will Hathaway, Neel Nanda, Dimitris Bertsimas. In TMLR. [arXiv][Twitter][Code]}

Algorithmic progress in language models
_{Anson Ho, Tamay Besiroglu, Ege Erdil, David Owen, Robi Rahman, Zifan Carl Guo, David Atkinson, Neil Thompson, Jaime Sevilla. In Neurips 2024. [arXiv]}

Measuring the Success of Diffusion Models at Imitating Human Artists
_{Stephen Casper*, Zifan Guo*, Shreya Mogulothu, Zachary Marinov, Chinmay Deshpande, Rui-Jie Yew, Zheng Dai, and Dylan Hadfield-Menell. Spotlighted in 2023 ICML Workshop on Generative AI and Law (GenLaw). (arXiv) (Twitter)}

Enabling Transformers to Understand Low-Level Programs
_{Zifan Carl Guo, and William Moses. In 2022 IEEE High Performance Extreme Computing Conference (HPEC).}