AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

Transformer language models have received widespread public attention, yet their
generated text is often surprising even to NLP researchers. In this survey, we discuss over …

Recent work has shown exciting promise in updating large language models with new
memories, so as to replace obsolete information or add specialized knowledge. However …

Research in mechanistic interpretability seeks to explain behaviors of machine learning
models in terms of their internal components. However, most previous work either focuses …

Transformer-based language models (LMs) are known to capture factual knowledge in their
parameters. While previous work looked into where factual associations are stored, only little …

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 …

Large language models based on transformers have achieved great empirical successes.
However, as they are deployed more widely, there is a growing need to better understand …

Despite rapid adoption and deployment of large language models (LLMs), the internal
computations of these models remain opaque and poorly understood. In this work, we seek …

\emph {Circuit analysis} is a promising technique for understanding the internal mechanisms
of language models. However, existing analyses are done in small models far from the state …

Large Language Models (LLMs) recently demonstrated extraordinary capability in various
natural language processing (NLP) tasks including language translation, text generation …