Skip to content

Delete dup divergent info in Main Demo, resolves #1415 #1416

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

Open
danra wants to merge 1 commit into
base: dev
Choose a base branch
from
+1 −9
Open

Delete dup divergent info in Main Demo, resolves #1415 #1416

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 1 addition & 9 deletions demos/Main_Demo.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -737,15 +737,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"TransformerLens supports 9,000+ models across 50+ architecture families, all of which can be loaded into a consistent(-ish) interface by just changing the name in `boot_transformers`. The available models are [documented here](https://transformerlensorg.github.io/TransformerLens/generated/transformer_bridge_models.html) with some notable ones [documented here](https://dynalist.io/d/n2ZWtnoYHrU1s4vnFSAQ519J#z=jHj79Pj58cgJKdq4t-ygK-4h), and a set of interpretability friendly models I've trained are [documented here](https://dynalist.io/d/n2ZWtnoYHrU1s4vnFSAQ519J#z=NCJ6zH_Okw_mUYAwGnMKsj2m), including a set of toy language models (tiny one to four layer models) and a set of [SoLU models](https://dynalist.io/d/n2ZWtnoYHrU1s4vnFSAQ519J#z=FZ5W6GGcy6OitPEaO733JLqf) up to GPT-2 Medium size (300M parameters)."

@jlarson4 jlarson4 Jun 22, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would like to maintain the very first link in this list that links to https://transformerlensorg.github.io/TransformerLens/generated/transformer_bridge_models.html. This is the current live list of supported models for main, and will update when the docs are rebuilt for the next release.

@danra danra Jun 22, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oops thanks for catching that, I meant to leave that one in place

@jlarson4 jlarson4 Jun 22, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No worries, thank you for all the cleanup you've been doing, it's very helpful.

]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"Notably, this means that analysis can be near immediately re-run on a different model by just changing the name - to see this, let's load in DistilGPT-2 (a distilled version of GPT-2, with half as many layers) and copy the code from above to see the induction heads in that model."
"TransformerLens supports 9,000+ models across 50+ architecture families, all of which can be loaded into a consistent(-ish) interface by just changing the name in `boot_transformers`. This means that analysis can be near immediately re-run on a different model by just changing the name - to see this, let's load in DistilGPT-2 (a distilled version of GPT-2, with half as many layers) and copy the code from above to see the induction heads in that model."
]
},
{
Expand Down
Loading