Manifund foxManifund
Home
Login
About
People
Categories
Newsletter
HomeAboutPeopleCategoriesLoginCreate
hzh avatarhzh avatar
Zhonghao He

@hzh

Master student in AI Ethics and Society at University of Cambridge; Thinking about mechanistic interpretability, neuroscience, ethics, and human-machine interaction.

hezhonghao.github.io
$0total balance
$0charity balance
$0cash balance

$0 in pending offers

Projects

Mapping neuroscience and mechanistic interpretability

Comments

Mapping neuroscience and mechanistic interpretability
hzh avatar

Zhonghao He

8 months ago

Progress update

What progress have you made since your last update?

  • We published a preprint at https://arxiv.org/abs/2408.12664v2!

  • I gave a talk at New England Mech Interp Workshop: https://nemiconf.github.io/summer24/schedule.html

What are your next steps?

  • I'll work on empirical works informed by the findings in this paper (send me an email if you want to collaborate!)

  • I'll give talks to interp & neuroscience groups on this topic (still let me know if you want me to give a talk in your lab!)

Is there anything others could help you with?

  • I'll need to raise new fund for further empirical works.

  • I'll need funding for academic trips.


Mapping neuroscience and mechanistic interpretability
hzh avatar

Zhonghao He

over 1 year ago

Thanks, Neel!

Both Wes & Cas have been very helpful.

We will be mostly focusing on an Arxiv preprint, and defer the decision on Nature at a later stage.

Transactions

ForDateTypeAmount
Manifund Bankabout 1 year agowithdraw500
Mapping neuroscience and mechanistic interpretability about 1 year agoproject donation+500
Manifund Bankover 1 year agowithdraw2400
Mapping neuroscience and mechanistic interpretability over 1 year agoproject donation+2400
Manifund Bankover 1 year agowithdraw3050
Mapping neuroscience and mechanistic interpretability over 1 year agoproject donation+100
Mapping neuroscience and mechanistic interpretability over 1 year agoproject donation+1200
Mapping neuroscience and mechanistic interpretability over 1 year agoproject donation+1750