通过正交约束让神经网络特征更清晰，减少混淆和冗余。
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
- 引入正交性约束，防止特征间互相吸收或混合。
- 发现9%更多独立特征，吸收问题降低65%。
- 适合研究模型可解释性与特征分离的学者。
稀疏自编码器（SAE）能将神经网络激活值分解为人类可理解的特征，但现有方法存在特征吸收（专业特征覆盖通用特征）和特征组合（独立特征合并成复合表示）问题。本文提出正交稀疏自编码器（OrtSAE），通过惩罚特征间高余弦相似度，强制学习正交特征，实现线性扩展且无显著计算开销。在多个模型和层上训练后，OrtSAE发现9%更多的独立特征，特征吸收减少65%，特征组合减少15%，在消除虚假相关性任务上性能提升6%，其他下游任务表现与传统SAE相当。
原文摘要 · Abstract (English)
Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of general features creating representation holes, and feature composition, where independent features merge into composite representations. In this work, we introduce Orthogonal SAE (OrtSAE), a novel approach aimed to mitigate these issues by enforcing orthogonality between the learned features. By implementing a new training procedure that penalizes high pairwise cosine similarity between SAE features, OrtSAE promotes the development of disentangled features while scaling linearly with the SAE size, avoiding significant computational overhead. We train OrtSAE across different models and layers and compare it with other methods. We find that OrtSAE discovers 9% more distinct features, reduces feature absorption (by 65%) and composition (by 15%), improves performance on spurious correlation removal (+6%), and achieves on-par performance for other downstream tasks compared to traditional SAEs.
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。