激活空间序交换几何：位点非对称性检验
Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit
- Substrate Labs
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对激活空间序交换几何提出位点非对称性检验，通过分解响应、在多类语言模型及非语言模型上开展实验，提出解读序交换向量的测量准则。
AI中文摘要：
依赖序的激活统计常被解释为交互作用的证据，但该解释可能因干预进入网络的位点而混淆。本文提出一种无拟合的位点非对称性检验。对于二次可微的读出函数，开路径序交换可分解为两类：由单次干预测得的规范加性响应，以及不含一阶和纯自曲率项的二阶反对称差。在6个开放权重语言模型家族中，单次干预基线解释了括号范数的84.3%-97.7%（均值93.7%）；在采用正负注入拆分的两个家族中，无交互作用的自曲率项比校正后的残差大1.8-5.2倍。在无混淆提示拆分下，校正后的残差在6个家族中的3个清除了通用交互作用的零假设；在配置鲁棒性检验后，6个家族中的2个满足该条件。已知的正代理可恢复植入的混合交互作用，匹配的位点分离测试会改变基线占比，随机架构可复现一阶机制。该估计量可迁移至非语言参考：在12个对比中（5/6个ViT-B/16、6/6个ResNet-50），训练后的残差分数低于固定高斯方向零假设，这是可迁移性检验而非合并证据。本文的贡献是提出可复用的测量准则：在将序交换向量解读为交互作用或几何结构前，先运行单次干预基线；若其能解释该向量，则改用二阶差。所有结论仅适用于不同位点的激活空间干预，不主张表示几何是全局阿贝尔的。
英文摘要：
Order-dependent activation statistics are often interpreted as evidence of interaction, but that interpretation can be confounded by where interventions enter the network. We introduce a no-fit site-asymmetry audit. For a twice-differentiable readout, the open-path order-swap decomposes into a canonical additive response measured by single interventions and an antisymmetrized second difference free of first-order and pure self-curvature terms to second order. Across six open-weight language-model families, the single-intervention baseline explains 84.3-97.7 percent of the bracket norm (mean 93.7 percent), while the no-interaction self-curvature term is 1.8-5.2 times larger than the corrected residual in the two families with the plus/minus injection split. The corrected residual clears a generic-interaction null in three of six families under a confound-free prompt split and two of six after configuration robustness. A known-positive surrogate recovers planted mixed interaction, while a matched site-separation test changes the baseline share and a random architecture reproduces the first-order regime. The same estimator transfers to released non-language references: trained residual fractions fall below a fixed Gaussian-direction null in 11/12 contrasts (5/6 ViT-B/16, 6/6 ResNet-50), a portability check rather than pooled evidence. The contribution is a reusable measurement criterion: run the single-intervention baseline before reading an order-swap vector as interaction or geometric structure; if it explains the vector, form the second difference instead. All claims are scoped to activation-space interventions at distinct sites; we do not claim that representation geometry is globally Abelian.
