Add interpretability subdir with sae

[jwilber]

Description

Moves over the interpretability code to recipes repository.

(I'm happy to restructure this as needed after GTC :D ).
The file structure is as follows:

bionemo-recipes/
    models/
    recipes/
    interpretability/
        sparse-autoencoders/
            sae/
            recipes/
                esm2/
                codonfm/

The idea is that, we may explore other interpretability techniques beyond SAEs, but if a user wants to find interpretability-focused recipes, they can come to bionemo-recipes and look in interpretability for the corresponding technique.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 06afad04-9186-4752-b698-d653b4d62089

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch jwilber/add-sae-interpretability

Tip

Try Coding Plans. Let us write the prompt for your AI agent so you can ship faster (with fewer bugs).
Share your feedback on Discord.

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[jwilber]

Don't review yet - i'll be making changes throughout the week (e.g. pointing to bionemo-hosted codonfm repo)