Fluent dreaming for language models (2402.01702v1)

Abstract: Feature visualization, also known as "dreaming", offers insights into vision models by optimizing the inputs to maximize a neuron's activation or other internal component. However, dreaming has not been successfully applied to LLMs because the input space is discrete. We extend Greedy Coordinate Gradient, a method from the LLM adversarial attack literature, to design the Evolutionary Prompt Optimization (EPO) algorithm. EPO optimizes the input prompt to simultaneously maximize the Pareto frontier between a chosen internal feature and prompt fluency, enabling fluent dreaming for LLMs. We demonstrate dreaming with neurons, output logits and arbitrary directions in activation space. We measure the fluency of the resulting prompts and compare LLM dreaming with max-activating dataset examples. Critically, fluent dreaming allows automatically exploring the behavior of model internals in reaction to mildly out-of-distribution prompts. Code for running EPO is available at https://github.com/Confirm-Solutions/dreamy. A companion page demonstrating code usage is at https://confirmlabs.org/posts/dreamy.html