New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Plan (New to Mech Interp? Try this after the other notebooks) #8

Open

poppingtonic opened this issue Apr 18, 2023 · 0 comments

Labels

enhancement good first issue

Milestone

Owner

poppingtonic commented Apr 18, 2023 •

edited

Possible updates to this project that I'm considering as I come up with plans for coming back to this project.

Validate Induction Heads for more LMs

Eigenvalues for detecting Induction Heads
NMF
More experiments with Activation Patching
[RLHF Reward Models]
- Linear Probes
- Episodic Linear Probes
Review Paper
- Does Mech-Interp Scale? https://arxiv.org/abs/2307.09458
- ROME (rank-one model editing) https://rome.baulab.info

poppingtonic added this to the 2023 milestone

poppingtonic added the enhancement label

poppingtonic mentioned this issue

Add Causal Influence Diagrams notebook #9

Merged

poppingtonic changed the title ~~Plan~~ Plan (New to Mech Interp? Try this after the other notebooks)

poppingtonic added the good first issue label

poppingtonic modified the milestones: Mech Interp Study Goals 2023, 2024

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment