Chris Olah - Looking Inside Neural Networks with Mechanistic Interpretability

Поделиться
HTML-код
  • Опубликовано: 27 окт 2024

Комментарии • 5

  • @epsilonlee9932
    @epsilonlee9932 Год назад +3

    Great talk and Q&A session by Chris, many insights there. Thanks for sharing this workshop!

  • @aidanlowrie4701
    @aidanlowrie4701 Год назад +2

    Fascinating! Thanks so much for making this publicly available.

  • @LeonidKotelnikov-jg9fi
    @LeonidKotelnikov-jg9fi Год назад

    superposition scares me

  • @OrlOnEarth
    @OrlOnEarth Год назад +4

    Set speed to 0.75x
    You're welcome 😂

  • @eoghanf
    @eoghanf Год назад +1

    Is it bullshit? LOL