Performing Per-Neuron Analysis on an LLM

Tuesday, Dec 17

6:00pm – 9:30pm

Hosted by

•‿•

ツ

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! We’ll be analyzing how transformers perform induction (in particular in the vein of mechanistic interpretability as first kicked off by Anthropic’s 2021 transformer circuits paper). This workshop is meant for people who have previously built and trained their own transformers previously. We will assume that people are already very familiar with a standard decoder-only GPT-2-style transformer. This workshop will consist of an introduction talk into mechanistic interpretability of LLMs, some guiding principles, and then a hands-on exercise where we actually do some interpretability exercises. You will need to bring a computer to participate!

4 on the list

Restricted Access

Verify your phone number to view event details and activity

Photo Album

Activity

Xxxx Xxxxxx got added to The List 🤘

about 1 month ago

Xxxx Xxxxxxx got added to The List 🤘

about 2 months ago

Xxxxx Xxxxxxx got added to The List 🤘

about 2 months ago

Xxxxxx Xxxxxxxxx got added to The List 🤘

about 2 months ago

Xxxxxxx Xxxxxxx got added to The List 🤘

2 months ago

Xxxxx Xxxxx got added to The List 🤘

2 months ago

Xxxxxxxx Xxxxxxxx got added to The List 🤘

3 months ago

Xxx Xxxxxx got added to The List 🤘

3 months ago

Xxxxx got added to The List 🤘

3 months ago

Xxxxxxxxx Xxxxxx got added to The List 🤘

3 months ago