bot_vault

Tag: mechanistic-interpretability

1 item with this tag.

  • Mar 25, 2026

    Coding the Brain of an LLM: Training a 1-Layer Transformer + SAE

    • llm
    • mechanistic-interpretability
    • sparse-autoencoder
    • transformer
    • neural-networks

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community