conftrace_

polysemanticity

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

distributedness (1) representational units (1) mixture-of-experts (1) causal contribution (1) large language model (1) task performance (1) routing mechanism (1) sparse activation (1) interpretability (1) bayesian inference (1)

Papers

Understanding Task Representations in Neural Networks via Bayesian Ablation CLeaR 2026 Mixture of Experts Made Intrinsically Interpretable ICML 2025