3 accepted papers
A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might represent *Ann loves pie* by binding *Ann* to *pie*, allowing it to later retrieve *Ann* when asked *Who loves pie?* Prior research on short lists of bound…
Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as “plants” or “the first word in a sentence”. These descriptions are derived using inputs that activate the feature, which may be a dimension or…
Large language models (LLMs) often acquire knowledge during pretraining that is undesirable in downstream deployments, e.g., sensitive information or copyrighted content. Existing approaches for removing such knowledge rely on fine-tuning, training low-rank adapters or fact-level editing, but these