New interpretability paper from Apollo Research! 🟢Attribution-based Parameter Decomposition 🟢 It's a new way to decompose neural network parameters directly into mechanistic components. It overcomes many of the issues with SAEs! 🧵

To my surprise, we find the opposite of what I thought when we started this project: The approach to reasoning LLMs use looks unlike retrieval, and more like a generalisable strategy synthesising procedural knowledge from many documents doing a similar form of reasoning.