AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Can We Decode the Internal Encodings of a Language Model?
Research is going beyond looking at the behavior of these models, and actually trying to make some stronger claims about the internal mechanisms that explain their behavior. That's a whole area of research that has come to be known as mechanistic interpretability in computer science and computational linguistics. We can take a leaf from the book of decades of research in neuroscience and psychology to try to understand the mechanisms of the black boxes that are the human mind or the human brain. The most refined kind of approach would be to look at toy models that are very, very small in terms of the number of parameters they have.