conftrace_

sanity checks

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

concept labels (1) desiderata (1) failure mode (1) fidelity metric (1) diversity metric (1) neuron explanation (1) evaluation metric (1) mechanistic interpretability (1) generative model (1) truthfulness (1)

Papers

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks ICML 2025 Position: All Current Generative Fidelity and Diversity Metrics are Flawed ICML 2025