Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Subfield
Interpretability of language models
Benchmarks: IOI circuit, MIB, SAEBench, RAVEL and others. Datasets: TinyStories, OpenWebText, Gemma Scope, CounterFact and others. Baselines: Linear probes, Integrated Gradients, Activation patching, ACDC and others.