Skip to content
conftrace_

feature circuit

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

mechanistic interpretability (2) circuit analysis (2) mlp layer (1) neural network (1) large language model (1) causal tracing (1) causal analysis (1) sparse autoencoder (1) model analysis (1) feature extraction (1)

Papers

Circuit-Tracer: A New Library for Finding Feature Circuits EMNLP 2025 Transcoders find interpretable LLM feature circuits NeurIPS 2024