How does chain of thought think? mechanistic interpretability of chain-of-thought reasoning with sparse autoencoding
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2026
Recommended citation: Xi Chen, Aske Plaat, Niki van Stein, "How does chain of thought think? mechanistic interpretability of chain-of-thought reasoning with sparse autoencoding." Proceedings of the AAAI Conference on Artificial Intelligence, 2026.
Use Google Scholar for full citation