Jump to Content

Nada Hussein

Authored Publications
results

Publications

Years

Research Areas

Teams

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Can Large Language Models Explain Their Own Thinking?
    Nithum Thain
    Nada Hussein
    Emily Reif
    Lucas Dixon
    Jimbo Wilson
    Asma Ghandeharioun
    Ryan Mullins
    (2024)
    Preview abstract An Explorable explaining the concept of patchoscopes for an external audience. Patchoscopes is an interpretability tool that allows researchers to better understand an LLMs output representations through natural language experiments. View details
    Can Large Language Models Explain Their Own Thinking?
    Nada Hussein
    Asma Ghandeharioun
    Ryan Mullins
    Emily Reif
    Jimbo Wilson
    Nithum Thain
    Lucas Dixon
    (2024)
    Preview abstract An Explorable explaining the concept of patchoscopes for an external audience. Patchoscopes is an interpretability tool that allows researchers to better understand an LLMs output representations through natural language experiments. View details
    Search on Google Scholar
    ×