Recent work has proposed that language models perform computation by manipulating one-
dimensional representations of concepts (" features") in activation space. In contrast, we …

Large Language Models (LLMs) have the capacity to store and recall facts. Through
experimentation with open-source models, we observe that this ability to retrieve facts can …

We analyze identifiability as a possible explanation for the ubiquity of linear properties
across language models, such as the vector difference between the representations of" …

Large Language Models (LLMs) are capable of producing content that perpetuates
stereotypes, discrimination, and toxicity. The recently proposed moral self-correction is a …

While large language models (LLMs) have demonstrated remarkable abilities across
various fields, hallucination remains a significant challenge. Recent studies have explored …

Causal language modeling using the Transformer architecture has yielded remarkable
capabilities in Large Language Models (LLMs) over the last few years. However, the extent …

Large Language Models (LLMs) are being used for a wide variety of tasks. While they are
capable of generating human-like responses, they can also produce undesirable output …

Transformer-based large language models (LLMs) have displayed remarkable creative
prowess and emergence capabilities. Existing empirical studies have revealed a strong …

Understanding how semantic meaning is encoded in the representation spaces of large
language models is a fundamental problem in interpretability. In this paper, we study the two …

When examined through the lens of their residual streams, a puzzling property emerges in
transformer networks: residual contributions (eg, attention heads) sometimes specialize in …