Andrew Mack

Produced as part of the MATS Winter 2024 program, under the mentorship of Alex Turner (TurnTrout). TL,DR: I introduce a method for eliciting latent behaviors in language models by learning unsupervised perturbations of an early layer of an LLM. These perturbations are trained to maximize changes in downstream activations. The method discovers diverse and meaningful behaviors with just one prompt, including perturbations overriding safety training, eliciting backdoored behaviors and uncovering latent capabilities. Summary In the simplest case, the unsupervised perturbations I learn are given by unsupervised steering vectors - vectors added to the residual stream as a bias term in the MLP outputs of a given layer. I also report preliminary results on unsupervised steering adapters - these are LoRA adapters of the MLP output weights of a given layer, trained with the same unsupervised objective. I apply the method to several alignment-relevant toy examples, and find that the method consistently learns vectors/adapters which encode coherent and generalizable high-level behaviors. Compared to other interpretability methods, I believe my approach is particularly well-suited for robustly understanding the out-of-distribution behavior of language models in a sample-efficient manner. Below are some of my key results: 1. Red-Teaming 1. I discover several anti-refusal steering vectors in Qwen-14B-Chat, based off a single prompt asking for bomb-making instructions. These can be grouped into "fantasy" vectors which induce bomb-making instructions since they interpret the prompt in the context of a specific fantasy game, as well as more troubling "real-world" vectors which induce real-world bomb-making advice. 2. I then investigate the generalization properties of the learned vectors: 1. In extended conversations with the real-world vectors, the LLM agrees to give detailed instructions for building weapons of mass destruction such as nuclear/chemical/biologic