conftrace_

distributed alignment search

3 papers

Explore in graph

Also known as

DAS

Co-occurring keywords · papers mentioning both

mechanistic interpretability (2) circuit localization (1) benchmark (1) causal variable (1) concept feature (1) causal interpretability (1) residual stream (1) linear probing (1) sparse autoencoder (1) language model (1)

Papers

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks ICLR 2025 MIB: A Mechanistic Interpretability Benchmark ICML 2025 CausalGym: Benchmarking causal interpretability methods on linguistic tasks ACL 2024