Eliciting Latent Predictions from Transformers with the Tuned Lens

We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer. To do so, we train an affine probe for each block in a frozen pretrained model, making it possible to decode every hidden state into a distribution over the vocabulary. Our method, the tuned lens, is a refinement of the earlier "logit lens" technique, which yielded useful insights but is often brittle. We test our method on various autoregressive language models with up to 20B parameters, showing it to be more predictive, reliable and unbiased than the logit lens. With causal experiments, we show the tuned lens uses similar features to the model itself. We also find the trajectory of latent predictions can be used to detect malicious inputs with high accuracy. All code needed to reproduce our results can be found at https://github.com/AlignmentResearch/tuned-lens.

On The Fragility of Learned Reward Functions

Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and preferences. Prior works on reward learning have mainly focused on the performance of policies trained alongside the reward function. This practice, however, may fail to detect learned rewards that are not capable of training new policies from scratch and thus do not capture the intended behavior. Our work focuses on demonstrating and studying the causes of these relearning failures in the domain of preference-based reward learning. We demonstrate with experiments in tabular and continuous control environments that the severity of relearning failures can be sensitive to changes in reward model design and the trajectory dataset composition. Based on our findings, we emphasize the need for more retraining-based evaluations in the literature.