检验单标记稀疏自编码器特征的因果必要性，发现其作用因模型层深和训练方法而异。
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects
- 通过零消融测试390万特征，验证单标记特征在解码空间中聚集于早期层且更紧密。
- 删除一个特征使208种层条件下178种出现目标词逻辑值下降，显著影响模型输出。
- 不同训练方法导致特征因果性差异，跨家族效果大于同一模型内规模变化。
稀疏自编码器（SAE）特征被用于解释和引导大语言模型，但尚未有人测试其因果角色在不同SAE族间是否稳定。单标记特征仅对一个词汇项激活，便于直接比较。我们分析了六种模型与三种SAE族共390万特征，并在完整层深度下进行零消融：这些特征在解码空间中聚集得更紧密（4.7倍紧致），主要集中在早期层。删除任一特征会使模型在208种层配置中的178种情况下该词的逻辑值下降，经多重比较校正后仍显著。层深决定损伤传递方式：早期层删除影响后续层，晚期层删除直接影响输出。跨族因果差异超过族内规模效应：同一基础模型上，GemmaScope与BatchTopK特征具因果锚定性，而LlamaScope特征局部冗余；在LlamaScope中，该词排名在消融后恢复至原始2倍内的概率为96%-98%。仅改变激活函数即可反转此差异符号，说明训练方案是剩余关键因素：跨族因果结论对训练方法敏感，不仅取决于激活函数或规模。
原文摘要 · Abstract (English)
Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet nobody has tested whether a feature's causal role is stable across SAE families. Single-token features fire on one vocabulary item, so ground truth permits direct comparison. We analyze 3.9M features across six models and three SAE families and zero-ablate at full layer depth: they sit 4.7x tighter in decoder space and concentrate in early layers. Deleting one lowers the model's logit for that token in 178 of 208 layer conditions, significant after multiple-comparison correction. And depth decides how the damage lands: early-layer deletions disrupt the layers that follow, late-layer deletions change the output directly. Cross-family causal differences exceed within-family scale effects: on the same base model, GemmaScope and BatchTopK features are causally anchored, LlamaScope features locally redundant. Under LlamaScope the token returns to within 2x its pre-ablation rank 96-98% of the time. Changing only the activation function reverses the sign of that difference, so the training recipe is the remaining candidate: cross-family claims are sensitive to training methodology, not just activation function or scale.
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。