发表机构
Astera Institute; UC Berkeley; UCL; Goodfire AI; CSHL（Astera研究所; 加州大学伯克利分校; 伦敦大学学院; Goodfire AI公司; 冷泉港实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出BeFOND，一种无编码器的稀疏编码模型，将推理与字典学习统一为自然梯度流，通过循环解释消除和Fisher预条件减少特征干扰并加速稀有特征学习，在合成数据和语言模型激活上显著提升字典恢复、稀有特征检测及概念干预效果。
AI 中文摘要
稀疏自编码器被广泛用于揭示神经网络中的可解释特征，然而当特征重叠或激活频率较低时，可靠的恢复仍然困难。这些挑战涉及推断哪些特征解释输入以及学习表示它们的字典。在这里，我们将推理和字典学习统一为共享变分自由能上的自然梯度流。我们将此框架实例化为BeFOND，一种无编码器的稀疏编码模型，具有闭式推理和学习动态。我们展示了循环解释消除如何减少重叠特征之间的干扰，而Fisher预条件可以补偿稀有特征的缓慢学习。在合成数据上，BeFOND提高了字典恢复和稀有特征检测，随着叠加增加，相对于摊销基线具有越来越大的优势。在语言模型激活上，它提高了单特征概念检测和选择性干预，以显著更少的训练数据优于预训练的参考SAE。其特征质量随字典宽度持续提高，而评估的基线大多趋于平稳。总之，这些结果展示了在统一概率框架内改进推理和学习如何能更好地利用数据和字典容量来解释和干预神经表示。
英文摘要
Sparse autoencoders are widely used to uncover interpretable features in neural networks, yet reliable recovery remains difficult when features overlap or activate infrequently. These challenges involve both inferring which features explain an input and learning the dictionary that represents them. Here, we unify inference and dictionary learning as natural-gradient flows on a shared variational free energy. We instantiate this framework as BeFOND, an encoder-free sparse coding model with closed-form inference and learning dynamics. We show how recurrent explaining away reduces interference between overlapping features, while Fisher preconditioning can compensate for the slow learning of rare features. On synthetic data, BeFOND improves dictionary recovery and rare-feature detection, with a growing advantage over amortized baselines as superposition increases. On language-model activations, it improves single-feature concept detection and selective intervention, outperforming pretrained reference SAEs with substantially less training data. Its feature quality continues to improve with dictionary width, whereas the evaluated baselines largely plateau. Together, these results show how improving inference and learning within a unified probabilistic framework can make better use of data and dictionary capacity to interpret and intervene on neural representations.
CommentsCode: https://github.com/hadivafaii/BeFOND
