Newest papers

Strength Controls Change How Interventions Compare Across Sparse Autoencoder Codes

Jinchen Zhang, Zheyuan Liu, Yihan Zhu, Meng Jiang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26489 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

设置稀缺的自动编码器(SAE)代码可以改变干预方向和大小,所以比较干预效果需要强度控制,指定什么被保持平等。标准匹配和输出校准提供不同的控制,但干预在强度匹配后对代码产生不同的效果仍然不清楚。我们在 Gemma 和 Llama 中对固定特征组(NNLS)的这些控制下比较干预效果,并观察到:(1)全套尺度。每输入一次总比值,全输出 Kullback-Leibler (KL) 校准会留下来自编码器基础的基准干预的平均效果差距较小,而不是总基准匹配的非负最低平方(NNLS)重复。在新的 Llama 输入中,全套尺度匹配损失了 11 个参

Machine translation (Meta M2M100); the English original follows.

Abstract

Changing sparse autoencoder (SAE) codes can alter both intervention direction and magnitude, so comparing intervention effects requires a strength control specifying what is held equal. Norm matching and output calibration provide different controls, but whether interventions yield different effects across codes after strength matching remains unclear. We compare intervention effects under these controls for fixed feature groups in Gemma and Llama and observe: (1) Whole-patch scaling. With one coefficient per input, full-output Kullback-Leibler (KL) calibration leaves smaller mean effect gaps from the encoder-based reference intervention than total-norm matching for nonnegative least-squares (NNLS) refits. On new Llama inputs, total-norm matching loses 11 reference transfers, whereas full-output calibration preserves every transfer decision. (2) Positionwise scaling. On a small matched gender-agreement subset, positionwise norm matching leaves smaller observed mean gaps than full-output calibration. (3) Answer exclusion. Compared with unscaled NNLS, answer-excluded calibration reduces gaps in the measured subject-verb agreement comparisons but increases them for gender refits. Full-output KL calibration also reduces larger gaps for norm-matched constructed candidates, although matching coverage is incomplete in several settings. Since calibration uses the evaluated input's outputs, it serves as a diagnostic of residual disagreement.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Matching (statistics), Calibration, Mathematics, Autoencoder, Residual, Norm (philosophy)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange