conftrace_

automated interpretability

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

feature description (2) mechanistic interpretability (2) sparse autoencoder (2) vision-language model (2) language model (2) steering evaluation (1) vocabulary unembedding (1) description evaluation (1) faithfulness metric (1) large language model (1)

Papers

Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability CVPR 2026 Language Models Can Explain Visual Features via Steering CVPR 2026 Enhancing Automated Interpretability with Output-Centric Feature Descriptions ACL 2025 FADE: Why Bad Descriptions Happen to Good Features ACL 2025 A Multimodal Automated Interpretability Agent ICML 2024 FIND: A Function Description Benchmark for Evaluating Interpretability Methods NeurIPS 2023