Are PPO-ed Language Models Hackable?

Numerous algorithms have been proposed to textitalign language models to remove undesirable behaviors. However, the challenges associated with a very large state space and creating a proper reward function often result in various jailbreaks. Our paper aims to examine this effect of reward in the controlled setting of positive sentiment language generation. Instead of online training of a reward model based on human feedback, we employ a statically learned sentiment classifier. We also consider a setting where our model's weights and activations are exposed to an end-user after training. We examine a pretrained GPT-2 through the lens of mechanistic interpretability before and after proximal policy optimization (PPO) has been applied to promote positive sentiment responses. Using these insights, we (1) attempt to "hack" the PPO-ed model to generate negative sentiment responses and (2) add a term to the reward function to try and alter `negative' weights.