Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Running causal interventions on a PyTorch model v1.0.0

Use this resource to test causal hypotheses on a model with activation patching

New

  • 562 downloads
  • 246 likes
  • 117 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install pyvene-causal-interventions

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent helps you install pyvene, define an intervention configuration declaratively, create an intervenable model, then run causal tracing or activation patching. It also presents interchange intervention training.

Mostly picked by

Updated November 2, 2026

Card for the “Running causal interventions on a PyTorch model” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: installation, intervention configuration and causal tracing
  • references/api.md, tutorials.md and README.md: API, tutorials and getting started

Good fit for

  • You study where a model stores a piece of information
  • You want reproducible, shareable intervention experiments

Not for

    Tags

    • interpretability
    • patching
    • causal
    • pytorch

    About

    You say

    “Run causal tracing on a GPT-2 model to locate the layer that stores a fact.”

    Card for the “Running causal interventions on a PyTorch model” skill

    Skill published by Orchestra Research under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to test causal hypotheses on a model with activation patching
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/api.md8.1 KB
    • references/README.md2.1 KB
    • references/tutorials.md10.2 KB
    • SKILL.md14.3 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/04-mechanistic-interpretability/pyvene
    Licence
    MIT

    Notice

    « pyvene-interventions » (Orchestra Research, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.