论文标题
叠加玩具模型
Toy Models of Superposition
论文作者
论文摘要
神经网络经常将许多无关的概念包装到一个神经元中 - 一种令人困惑的现象被称为“多疾病”，这使解释性更具挑战性。本文提供了一个玩具模型，可以完全理解多概念性，这是由于模型中存储了“叠加”中其他稀疏特征的结果。我们证明了相变的存在，与均匀多型的几何形状的令人惊讶的联系以及与对抗性实例联系的证据。我们还讨论了对机械解释性的潜在影响。
Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This paper provides a toy model where polysemanticity can be fully understood, arising as a result of models storing additional sparse features in "superposition." We demonstrate the existence of a phase change, a surprising connection to the geometry of uniform polytopes, and evidence of a link to adversarial examples. We also discuss potential implications for mechanistic interpretability.
