Mechanistic interpretability research faces a gap between analyzing simple circuits in toy tasks and discovering features in large models. To bridge this gap, we propose text-to-SQL generation as an ideal task to study, as it combines the formal structure of toy tasks with real-world complexity. We introduce TinySQL, a synthetic dataset progressing from basic to advanced SQL operations, and train models ranging from 33M to 1B parameters to establish a comprehensive testbed for interpretability. We apply multiple complementary interpretability techniques, including edge attribution patching and sparse autoencoders, to identify minimal circuits and components supporting SQL generation. Our analysis reveals both the potential and limitations of current interpretability methods, showing how circuits can vary even across similar queries. Lastly, we demonstrate how mechanistic interpretability can identify flawed heuristics in models and improve synthetic dataset design. Our work provides a comprehensive framework for evaluating and advancing interpretability techniques while establishing clear boundaries for their reliable application.
View on arXiv@article{quirke2025_2503.12730,
title={ TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research },
author={ Philip Quirke and Clement Neo and Abir Harrasse and Dhruv Nathawani and Amir Abdullah },
journal={arXiv preprint arXiv:2503.12730},
year={ 2025 }
}