LLM Layers Immediately Correct Each Other

2026-09-07

Neural Information Processing Systems

AI Summary

研究通过识别Transformer层校正机制(TLCM)，挑战了现有语言模型解释方法的观点，揭示相邻层间如何相互纠正贡献，并提出一种‘提议-拒绝’框架。

Abstract

Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linear, semantically meaningful features. Such methods are commonly interpreted as identifying features that persist in the residual stream and that subsequent layers build upon. We challenge this view by identifying the Transformer Layer Correction Mechanism (TLCM), wherein adjacent transformer layers systematically counteract portions of each other's contributions. TLCM appears in 5 out of 7 major open-source model families and activates across nearly all tokens in diverse texts. We show that TLCM emerges during pretraining, operates most strongly on contextually dependent tokens, and adaptively calibrates its correction strength based on the preceding layer's output. Using the layer Jacobian, we further show that TLCM selectively corrects specific subspaces while reinforcing others, which we interpret through a ``propose-and-reject''framework in which layers propose candidate features and subsequent layers selectively remove inappropriate ones. This dynamic suggests that the residual stream at any layer contains transient proposals alongside persistent features, helping explain why SAE feature descriptions often have low specificity, why effective model steering requires extreme feature amplification, and why transcoders hold a theoretical advantage over SAEs.

Problem

• Transformer Layer Correction Mechanism
• residual stream
• language model interpretability
• contextually dependent tokens

Innovation

• Transformer Layer Correction Mechanism
• Propose-and-Reject Framework
• Layer Jacobian