Research papers

Real Sparks of Artificial Intelligence and the Importance of Inner Interpretability

The present paper looks at one of the most thorough articles on the intelligence of GPT, research conducted by engineers at Microsoft. Although there is a great deal of value in their work, I will argue that, for familiar philosophical reasons, their methodology, !Blackbox Interpretability"#is wrongheaded. But there is a better way. There is an exciting and emerging discipline of !Inner Interpretability"#(and specifically Mechanistic Interpretability) that aims to uncover the internal activations and weights of models in order to understand what they represent and the algorithms they implement. In my view, a crucial mistake in Black-box Inter