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

• URL: http://arxiv.org/abs/2507.22928v1
• Date: Thu, 24 Jul 2025 10:25:46 GMT
• Title: How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
• Authors: Xi Chen, Aske Plaat, Niki van Stein,
• Abstract summary: Chain-of-thought (CoT) prompting boosts Large Language Models accuracy on multi-step tasks.<n>But whether the generated "thoughts" reflect the true internal reasoning process is unresolved.<n>We present the first feature-level causal study of CoT faithfulness.
• Score: 3.8914132324834045
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chain-of-thought (CoT) prompting boosts Large Language Models accuracy on multi-step tasks, yet whether the generated "thoughts" reflect the true internal reasoning process is unresolved. We present the first feature-level causal study of CoT faithfulness. Combining sparse autoencoders with activation patching, we extract monosemantic features from Pythia-70M and Pythia-2.8B while they tackle GSM8K math problems under CoT and plain (noCoT) prompting. Swapping a small set of CoT-reasoning features into a noCoT run raises answer log-probabilities significantly in the 2.8B model, but has no reliable effect in 70M, revealing a clear scale threshold. CoT also leads to significantly higher activation sparsity and feature interpretability scores in the larger model, signalling more modular internal computation. For example, the model's confidence in generating correct answers improves from 1.2 to 4.3. We introduce patch-curves and random-feature patching baselines, showing that useful CoT information is not only present in the top-K patches but widely distributed. Overall, our results indicate that CoT can induce more interpretable internal structures in high-capacity LLMs, validating its role as a structured prompting method.

Related papers

• How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation [9.455881608413137]
  Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanisms remain poorly understood.<n>We analyze CoT's operational principles by reversely tracing information flow across decoding, projection, and activation phases.
  arXiv  Detail & Related papers  (2025-07-28T12:11:16Z)
• R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning [60.37610817226533]
  Chain-of-thought (CoT) reasoning encourages step-by-step intermediate reasoning during inference.<n>CoT introduces substantial computational overhead due to its reliance on autoregressive decoding over long token sequences.<n>We present R-Stitch, a token-level, confidence-based hybrid decoding framework that accelerates CoT inference.
  arXiv  Detail & Related papers  (2025-07-23T08:14:36Z)
• Prompting Science Report 2: The Decreasing Value of Chain of Thought in Prompting [0.0]
  Chain-of-Thought (CoT) prompting is a technique that encourages a large language model to "think step by step"<n>The effectiveness of CoT prompting can vary greatly depending on the type of task and model.<n>For models designed with explicit reasoning capabilities, CoT prompting often results in only marginal, if any, gains in answer accuracy.
  arXiv  Detail & Related papers  (2025-06-08T13:41:25Z)
• CoT-Valve: Length-Compressible Chain-of-Thought Tuning [50.196317781229496]
  We introduce a new tuning and inference strategy named CoT-Valve, designed to allow models to generate reasoning chains of varying lengths.<n>We show that CoT-Valve successfully enables controllability and compressibility of the chain and shows better performance than the prompt-based control.
  arXiv  Detail & Related papers  (2025-02-13T18:52:36Z)
• Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding [74.31981011985681]
  Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures.
  arXiv  Detail & Related papers  (2024-11-06T22:02:30Z)
• To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning [55.52872152909785]
  Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs)<n>We show that CoT gives strong performance benefits primarily on tasks involving math or logic, with much smaller gains on other types of tasks.
  arXiv  Detail & Related papers  (2024-09-18T17:55:00Z)
• Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs [63.36637269634553]
  We introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.<n>We show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales.<n>Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)
• Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions [10.621564997491808]
  Chain-of-thought (CoT) prompting has been shown to empirically improve the accuracy of large language models. We investigate whether CoT prompting affects the relative importances they assign to particular input tokens. Our results indicate that while CoT prompting does not increase the magnitude of saliency scores attributed to semantically relevant tokens in the prompt, it increases the robustness of saliency scores to question perturbations and variations in model output.
  arXiv  Detail & Related papers  (2023-07-25T08:51:30Z)
• Measuring Faithfulness in Chain-of-Thought Reasoning [19.074147845029355]
  Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question. It is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning (i.e., its process for answering the question) We investigate hypotheses for how CoT reasoning may be unfaithful, by examining how the model predictions change when we intervene on the CoT.
  arXiv  Detail & Related papers  (2023-07-17T01:08:39Z)
• Multimodal Chain-of-Thought Reasoning in Language Models [94.70184390935661]
  We propose Multimodal-CoT that incorporates language (text) and vision (images) modalities into a two-stage framework. Experimental results on ScienceQA and A-OKVQA benchmark datasets show the effectiveness of our proposed approach.
  arXiv  Detail & Related papers  (2023-02-02T07:51:19Z)
• Faithful Chain-of-Thought Reasoning [51.21714389639417]
  Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of reasoning tasks. We propose Faithful CoT, a reasoning framework involving two stages: Translation and Problem Solving. This guarantees that the reasoning chain provides a faithful explanation of the final answer.
  arXiv  Detail & Related papers  (2023-01-31T03:04:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.