Decomposing Language Models Into Understandable Components

Introduced dictionary learning to decompose transformer model layers into more interpretable features (patterns of neuron activations). Demonstrated that these features are significantly more interpretable than individual neurons through human evaluation and autointerpretability scoring. Showcased that activating features predictably steers model behavior. Found features to be largely universal across different models and that tuning the number of features provides a resolution knob for model understanding. This work addresses a roadblock in mechanistic interpretability by moving beyond individual neuron analysis.