Inspecting the information encoded in hidden representations of large language models (LLMs) can explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose leveraging the model itself to explain its internal representations in natural language. We introduce a framework called Patchscopes and show how it can be used to answer a wide range of research questions about an LLM's computation. We show that prior interpretability methods based on projecting representations into the vocabulary space and intervening on the LLM computation, can be viewed as special instances of this framework. Moreover, several of their shortcomings such as failure in inspecting early layers or lack of expressivity can be mitigated by a Patchscope. Beyond unifying prior inspection techniques, Patchscopes also opens up new possibilities such as using a more capable model to explain the representations of a smaller model, and unlocks new applications such as self-correction in multi-hop reasoning.

翻译：摘要：检查大型语言模型（LLM）隐藏表示中编码的信息，可以解释模型的行为并验证其与人类价值观的一致性。鉴于LLM生成人类可理解文本的能力，我们提出利用模型自身以自然语言解释其内部表示。我们引入一个名为Patchscope的框架，并展示如何将其用于回答关于LLM计算的广泛研究问题。我们表明，先前基于将表示投影到词汇空间以及对LLM计算进行干预的可解释性方法，可视为该框架的特例。此外，这些方法的若干缺陷（例如无法检查早期层或缺乏表达能力）可通过Patchscope得到缓解。除了统一先前的检查技术外，Patchscope还开辟了新的可能性，例如使用能力更强的模型来解释较小模型的表示，并解锁了新的应用场景，如多跳推理中的自我纠正。