A. Plaat

Papers on Lattice

Total citations

Topics

h-index

Research focus

Interpretability & Mechanistic Interp (1)Reasoning & Chain-of-Thought (1)

Frequent co-authors

Xi Chen (1)N. V. Stein (1)

Papers (1)

Jul 24, 2025

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding

Chain-of-thought reasoning isn't just window dressing: swapping CoT-related features into smaller LLMs reveals a scale threshold where it actually steers the model towards correct answers.

Xi Chen, A. Plaat, N. V. Stein7

Interpretability & Mechanistic Interp Reasoning & Chain-of-Thought

Search

A. Plaat

Research focus

Frequent co-authors

Papers (1)