How does chain of thought think? mechanistic interpretability of chain-of-thought reasoning with sparse autoencoding
Published in arXiv preprint arXiv:2507.22928, 2025
Recommended citation: Xi Chen, Aske Plaat, Niki Stein, "How does chain of thought think? mechanistic interpretability of chain-of-thought reasoning with sparse autoencoding." arXiv preprint arXiv:2507.22928, 2025.
Use Google Scholar for full citation