Overview
What this challenge is about.
Probe a frozen BERT encoder on POS, dependency arcs, and semantic role labeling. Plot accuracy by layer. Earn a verifiable certificate.
The scenario
The university spinout (around 30 researchers, EU-funded interpretability research) ships probing studies as part of its grant-deliverable cadence.
The Brief
What you'll do, and what you'll demonstrate.
Run a layer-wise probing study on a pretrained encoder with selectivity controls and write the workshop report.
Earning criteria — what you'll demonstrate
- Implement layer-wise probing with proper controls
- Quantify what linguistic knowledge each transformer layer encodes
- Apply probe selectivity to avoid overclaiming
- Write a workshop-style interpretability report
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Interpretability
Apply interpretability to solve real industry problems and demonstrate production-level capability.
- Probing
Apply probing to solve real industry problems and demonstrate production-level capability.
- Transformers
Apply transformers to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Linguistic Evaluation
Apply linguistic evaluation to solve real industry problems and demonstrate production-level capability.
- Scientific Writing
Apply scientific writing to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
ML Researcher
Layer-wise probing and selectivity analysis is the canonical interpretability work that ML researchers do on representation-learning teams.
This challenge sharpens
- interpretability
- probing
- transformers
Research Scientist
Following established protocols rigorously and reporting honestly with proper controls is the rigor expected of a junior research scientist on an interpretability team.
This challenge sharpens
- probing
- scientific-writing
- linguistic-evaluation
AI Safety Researcher
Interpretability skills bridge directly into AI safety research, where understanding what models know is foundational to alignment work.
This challenge sharpens
- interpretability
- probing
- scientific-writing