用增强学习让旧的稀疏自编码器学会新领域的特征。
Teach Old SAEs New Domain Tricks with Boosting
- 用次级自编码器捕捉主模型在特定领域遗漏的重建误差。
- 在多个专业领域中，交叉熵和解释方差显著提升。
- 无需重训，可针对性增强模型可解释性，适合研究特定领域。
稀疏自编码器（SAE）已成为解析大语言模型内部表征的强大工具，但常因训练语料不包含特定领域特征而无法捕捉这些特征。本文提出一种残差学习方法，在不重新训练的前提下解决这一问题。通过训练一个次级SAE专门建模预训练SAE在领域文本上的重建误差，有效捕获主模型遗漏的特征。推理时将两个模型输出相加，实验表明该方法在多个专业领域中均显著提升了大语言模型的交叉熵与解释方差指标。该方法能高效融入新领域知识，同时保持通用任务性能，使研究人员可选择性增强特定领域的可解释性，为大语言模型的定向机制解析开辟新路径。
原文摘要 · Abstract (English)
Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features not prevalent in their training corpora. This paper introduces a residual learning approach that addresses this feature blindness without requiring complete retraining. We propose training a secondary SAE specifically to model the reconstruction error of a pretrained SAE on domain-specific texts, effectively capturing features missed by the primary model. By summing the outputs of both models during inference, we demonstrate significant improvements in both LLM cross-entropy and explained variance metrics across multiple specialized domains. Our experiments show that this method efficiently incorporates new domain knowledge into existing SAEs while maintaining their performance on general tasks. This approach enables researchers to selectively enhance SAE interpretability for specific domains of interest, opening new possibilities for targeted mechanistic interpretability of LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。