The Importance of Prompt Tuning for Automated Neuron Explanations
This work addresses the need for better interpretability and safety in LLMs, but it is incremental as it builds on prior methods for neuron explanation.
The paper tackled the problem of understanding large language models by studying individual neurons, showing that reformatting the prompt for generating explanations significantly improves quality and reduces computational cost.
Recent advances have greatly increased the capabilities of large language models (LLMs), but our understanding of the models and their safety has not progressed as fast. In this paper we aim to understand LLMs deeper by studying their individual neurons. We build upon previous work showing large language models such as GPT-4 can be useful in explaining what each neuron in a language model does. Specifically, we analyze the effect of the prompt used to generate explanations and show that reformatting the explanation prompt in a more natural way can significantly improve neuron explanation quality and greatly reduce computational cost. We demonstrate the effects of our new prompts in three different ways, incorporating both automated and human evaluations.