Do Sparse Autoencoders Identify Reasoning Features in Language Models?
We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain stable low-dimensional correlates while suppressing high-dimensional within-behavior variation, motivating the possibility that contrastively selected "reasoning" features may concentrate on cue-like structure when such cues are coupled with reasoning traces. Building on this perspective, we propose a falsification-based evaluation framework that combines causal token injection with LLM-guided counterexample construction. Across 22 configurations spanning multiple model families, layers, and reasoning datasets, we find that many contrastively selected candidates are highly sensitive to token-level interventions, with 45%-90% activating after injecting only a few associated tokens into non-reasoning text. For the remaining context-dependent candidates, LLM-guided falsification produces targeted non-reasoning inputs that trigger activation and meaning-preserving paraphrases of top-activating reasoning traces that suppress it. A small steering study yields minimal changes on the evaluated benchmarks. Overall, our results suggest that, in the settings we study, sparse decompositions can favor low-dimensional correlates that co-occur with reasoning, underscoring the need for falsification when attributing high-level behaviors to individual SAE features. Code is available at https://github.com/GeorgeMLP/reasoning-probing.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Large Language Models (LLMs) have achieved remarkable success in natural language processing. Recent advances have led to the developing of a new class of reasoning LLMs; for example, open-source DeepSeek-R1 has achieved…
AllTriggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that triggers this behavior remains poorly understood. Leveraging the sparse features cap…
Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer
Large language models exhibit substantial performance variation across languages, even when solving semantically equivalent tasks. Existing analyses often treat this phenomenon as an observational disparity caused by dif…
Steering Language Model Refusal with Sparse Autoencoders
Responsible practices for deploying language models include guiding models to recognize and refuse answering prompts that are considered unsafe, while complying with safe prompts. Achieving such behavior typically requir…
Language ModelingLanguage ModellingmodelA Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering
Sparse autoencoders (SAEs) have recently emerged as a powerful tool for language model steering. Prior work has explored top-k SAE latents for steering, but we observe that many dimensions among the top-k latents capture…
Mathematical Reasoning