Automatically Finding Rule-Based Neurons in OthelloGPT

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Singh, Aditya, Wen, Zihang, Medicherla, Srujananjali, Karvonen, Adam, Rager, Can
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908623000567808
author Singh, Aditya
Wen, Zihang
Medicherla, Srujananjali
Karvonen, Adam
Rager, Can
author_facet Singh, Aditya
Wen, Zihang
Medicherla, Srujananjali
Karvonen, Adam
Rager, Can
contents OthelloGPT, a transformer trained to predict valid moves in Othello, provides an ideal testbed for interpretability research. The model is complex enough to exhibit rich computational patterns, yet grounded in rule-based game logic that enables meaningful reverse-engineering. We present an automated approach based on decision trees to identify and interpret MLP neurons that encode rule-based game logic. Our method trains regression decision trees to map board states to neuron activations, then extracts decision paths where neurons are highly active to convert them into human-readable logical forms. These descriptions reveal highly interpretable patterns; for instance, neurons that specifically detect when diagonal moves become legal. Our findings suggest that roughly half of the neurons in layer 5 can be accurately described by compact, rule-based decision trees ($R^2 > 0.7$ for 913 of 2,048 neurons), while the remainder likely participate in more distributed or non-rule-based computations. We verify the causal relevance of patterns identified by our decision trees through targeted interventions. For a specific square, for specific game patterns, we ablate neurons corresponding to those patterns and find an approximately 5-10 fold stronger degradation in the model's ability to predict legal moves along those patterns compared to control patterns. To facilitate future work, we provide a Python tool that maps rule-based game behaviors to their implementing neurons, serving as a resource for researchers to test whether their interpretability methods recover meaningful computational structures.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00059
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automatically Finding Rule-Based Neurons in OthelloGPT
Singh, Aditya
Wen, Zihang
Medicherla, Srujananjali
Karvonen, Adam
Rager, Can
Machine Learning
Artificial Intelligence
OthelloGPT, a transformer trained to predict valid moves in Othello, provides an ideal testbed for interpretability research. The model is complex enough to exhibit rich computational patterns, yet grounded in rule-based game logic that enables meaningful reverse-engineering. We present an automated approach based on decision trees to identify and interpret MLP neurons that encode rule-based game logic. Our method trains regression decision trees to map board states to neuron activations, then extracts decision paths where neurons are highly active to convert them into human-readable logical forms. These descriptions reveal highly interpretable patterns; for instance, neurons that specifically detect when diagonal moves become legal. Our findings suggest that roughly half of the neurons in layer 5 can be accurately described by compact, rule-based decision trees ($R^2 > 0.7$ for 913 of 2,048 neurons), while the remainder likely participate in more distributed or non-rule-based computations. We verify the causal relevance of patterns identified by our decision trees through targeted interventions. For a specific square, for specific game patterns, we ablate neurons corresponding to those patterns and find an approximately 5-10 fold stronger degradation in the model's ability to predict legal moves along those patterns compared to control patterns. To facilitate future work, we provide a Python tool that maps rule-based game behaviors to their implementing neurons, serving as a resource for researchers to test whether their interpretability methods recover meaningful computational structures.
title Automatically Finding Rule-Based Neurons in OthelloGPT
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.00059