稀疏读出棱镜：从特征而非词元层面解释 Logit 透镜得分

摘要

语言模型对下一个token的预测逐层形成，透镜方法通过将中间隐藏状态解码为token来追踪这一过程。然而，一次透镜读数既反映了隐藏状态，也反映了用于解码该状态的读出层（即去嵌入矩阵）。许多透镜是在某个语料库上拟合得到的；我们表明，仅拟合语料库不同的两个透镜，对相同的隐藏状态可能报告出不同的token。我们将这种依赖称为语料条件性。为了在不依赖拟合语料库的情况下考察读出层结构，我们引入了稀疏读出棱镜（Sparse Readout Prism, SRP）。它仅利用读出层的权重对读出层进行分解，并将任意token的logit或logit差值表示为来自稀疏读出特征的贡献之和。这使读出特征成为透镜读数的一种新分析单元，揭示出可能被token身份所遮蔽的结构，并支持在token、上下文、层和透镜之间进行比较。用SRP的稀疏近似替换原始读出层，比基于读出行间几何关系的六个基线中最强的一个，多重构了8.9—17.3个百分点的测试logit差值。对特征进行消融，会使logit差值按其特征的SRP贡献成比例偏移。尽管token读数随拟合语料库而变化，但主导的读出特征保持稳定。由于SRP在构建时不使用任何语料库，它为透镜分析提供了一个独立于拟合语料库的对照。

English

A language model's prediction of its next token develops across layers, and lens methods track this process by decoding intermediate hidden states into tokens. But a lens reading reflects both the hidden state and the readout (the unembedding matrix) used to decode it. Many lenses are fit on a corpus, and we show that two lenses differing only in their fitting corpus can report different tokens for the same hidden states. We call this dependence corpus conditionality. To examine readout structure independently of the fitting corpus, we introduce Sparse Readout Prism (SRP), which decomposes the readout using only its weights and expresses any token logit or logit difference as a sum of contributions from sparse readout features. This reveals readout features as a new unit of analysis for lens readings, exposing structure that token identities can obscure and enabling comparisons across tokens, contexts, layers, and lenses. Replacing the original readout with SRP's sparse approximation reconstructs 8.9-17.3 percentage points more of the tested logit differences than the strongest of six baselines built on geometric relations among readout rows. Ablating features shifts logit differences in proportion to their SRP contributions. Although token readings vary with the fitting corpus, the dominant readout feature remains stable. Because SRP uses no corpus in its construction, it provides a control independent of the fitting corpus for lens analyses.