brightlabYear 12 · Live trained model and learned-weight decomposition · 55 minutes
Take the weights apart
Does a neat decomposition preserve the behaviour we care about?
The first load downloads Python and may take a moment. Write a prediction, then open the lab. Controls, help, teacher notes and your evidence download are inside. If the school network blocks the runtime, download the Python notebook and run it with your teacher.
Investigate one research connection
Interpreting Language Model Parameters
Compare exact reconstruction, component removal and behavioural tests of a decomposition. Record the source model/task, a baseline, the changed factor, a measurement and an alternative explanation. State exactly which part your notebook investigates and which part it does not reproduce.
Our SVD exercise is a contrast, not VPD. The paper studies a 67M-parameter model, not all frontier models.
Use the notebook below to collect the measurements. This writing remains in this page session until downloaded.
Teacher background and source method
A four-layer 67M language model trained on the Pile
Learns parameter subcomponents and causal importance with VPD; evaluates reconstruction, sparsity, interventions and robustness against alternative decompositions.
Independent classroom adaptation; not a reproduction of the source model or complete method.
Read the source with a teacher ↗Opening the notebook page…
First use downloads Python and its libraries. A fresh session measured about 20–22 seconds and 14–17 MB during the initial audit; school networks vary. This hosted notebook computes on the browser CPU.
Your prediction and saved runs stay in this session. Download your evidence before leaving or refreshing. The hosted experiment runs on your browser CPU and does not connect to an H100.
Research connections · 5 archive entries
These lessons adapt ideas and methods. The original sources state their own model, data and validation scope.
Interpreting Language Model Parameters ↗
Our SVD exercise is a contrast, not VPD. The paper studies a 67M-parameter model, not all frontier models.
Towards Scalable Parameter Decomposition ↗
SPD evidence here is based on controlled models; the SVD notebook is a baseline contrast, not an SPD implementation.
Understanding Memorization via Loss Curvature ↗
The source uses curvature approximations including K-FAC; our exact quadratic toy is not a K-FAC replication. Edits have collateral costs.
Paper Summary: Interpreting Language Model Parameters ↗
This explains the same work as Interpreting Language Model Parameters; it is not a second independent result.
Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention ↗
The reported mechanism is studied in particular toy and language models; size is not a guarantee on every task.