N2G: A SCALABLE APPROACH FOR QUANTIFYING INTERPRETABLE NEURON REPRESENTATION IN LLMS

Alex Foote, Neel Nanda, Esben Kran, Ioannis Konstas, Fazl Barez

Keywords: Interpretability

TL;DR: We introduce N2G, a method for converting neurons in LLMs into interpretable graphs which can be visualized and automatically evaluated.

Abstract: Understanding the function of individual neurons within language models is essential for mechanistic interpretability research. We propose Neuron to Graph (N2G), a tool which takes a neuron and its dataset examples, and automatically distills the neuron’s behaviour on those examples to an interpretable graph. This presents a less labour intensive approach to interpreting neurons than current manual methods, that will better scale these methods to LLMs. We use truncation and saliency methods to only present the important tokens, and augment the dataset examples with more diverse samples to better capture the extent of neuron behaviour. These graphs can be visualised to aid manual interpretation by researchers, but can also output token activations on text to compare to the neuron’s ground truth activations for automatic validation. N2G represents a step towards scalable interpretability methods by allowing us to convert neurons in an LLM to interpretable representations of measurable quality.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/n2g-a-scalable-approach-for-quantifying/code)