Skip to content
This repository was archived by the owner on Jul 17, 2026. It is now read-only.
This repository was archived by the owner on Jul 17, 2026. It is now read-only.

Investigating whether SPD is stable to training with a subset of the data #4

Description

@danbraunai

Migrated from: goodfire-ai/spd-gf#67
Original author: @leesharkey


We’d like to evaluate if the method is stable during training with a subset of the dataset. We think this is important to ensure training at scale actually works. This is because, as we scale, our SPD model will increasingly see less and less of the training dataset in a time-window of a fixed size.

The approach here is to take e.g. a trained TMS model and then try to decompose the network using a dataset that is different from the training distribution. In particular, train it using a dataset where some of the features are always off.

In an ideal world, we would like PD to decompose the network into components that correspond to the active features and ‘the rest’, where the rest includes the features that weren’t active in the PD training dataset. The purpose of this experiment is to test the robustness of PD to distributional shift.

Another way to test this if the above succeeds: First do the above and get your decomposition components corresponding to ‘active’ and ‘the rest’ components. Then, start a new phase of PD training that uses the originalTMS dataset. See if it transitions gracefully. (it might not transition if, for instance, gates have been turned off. This matters for stability of general)

Metadata

Metadata

Assignees

No one assigned

    Labels

    Priority: InUImportant & not Urgentexp/investigationA research investigation or experiment

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions