Name: Performing Per-Neuron Analysis on an LLM
Start: 2024-12-17T18:00:00-05:00
End: 2024-12-17T21:30:00-05:00
Location: Homebrew

Ever wonder how transformers actually do some of their computation? Wanted to know more about what this "mechanistic interpretability" thing is and how it relates to AI safety? This is the workshop for you!

Please see [https://aisafetyawarenessfoundation.org/workshops/nyc-dec-2024-2/](https://aisafetyawarenessfoundation.org/workshops/nyc-dec-2024-2/) for more details.

Changlin Li

AI Safety Awareness Group New York City

Technology

Artificial Intelligence

New Technology

Machine Learning

Technology Startups

Artificial Intelligence Applications

AI and Society

AI Algorithms

Future Progress in Artificial Intelligence

Performing Per-Neuron Analysis on an LLM

Homebrew

Share this event

Performing Per-Neuron Analysis on an LLM

Details