Sprint projectApr 4, 2025
Mechanisms of Casual Reasoning
Ben Sturgeon, Jacy Reese Anthis, Mark Chimes, Sky Cope
Submitted to The Interpretability Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.
Causal reasoning is a crucial part of how we humans safely and robustly think about the world. Can we identify if LLMs have causal reasoning? Marius Hobbhahn and Tom Lieberum (2022, Alignment Forum) approached this with probing. For this hackathon, we follow-up on that work by exploring a mechanistic interpretability analysis of causal reasoning in the 80 million parameters of GPT-2 Small using Neel Nanda’s Easy Transformer package.
Reviews
Judging this Sprint?
No public critique yet.
Cite this project
@misc{sturgeon2025mechanisms,
title = {{Mechanisms of Casual Reasoning}},
author = {Ben Sturgeon and Jacy Reese Anthis and Mark Chimes and Sky Cope},
year = {2025},
month = apr,
note = {Submitted to The Interpretability Hackathon, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/mechanisms-of-causal-reasoning}},
url = {https://apartresearch.com/sprints/projects/mechanisms-of-causal-reasoning}
}Browse all projects