if_Guo

Popular Tags
#interpretability#LLM#optimization#weight-geometry#agentic-RL#neural-network#implicit-regularization#mathematics#model-compression#reparameterization
Home

❯

Topics

❯

interpretability

Folder: Topics/interpretability

5 items under this folder.

  • Jul 20, 2026

    LLM 机制可解释性:一条方法谱系

    • interpretability
  • Jul 20, 2026

    读残差流:Logit Lens 到 Patchscopes

    • interpretability
  • Jul 20, 2026

    2025 前沿:谱系的收敛与对地基的反思

    • interpretability
  • Jul 20, 2026

    特征与叠加:字典学习这条线

    • interpretability
  • Jul 20, 2026

    干预与电路:从 Causal Tracing 到自动电路发现

    • interpretability

Created with Quartz v4.4.1 © 2026