Linear Probing for Interpretability
InterviewConceptualinterpretabilityprobingrepresentations
Related module: Evaluation and interpretability
Problem statement
Linear probes are used to understand what information is encoded in neural network representations.
- What is a linear probe and how is it trained?
- If a linear probe achieves high accuracy, what can and can't we conclude?
- Design a probing experiment to test if a language model encodes syntactic structure.