Mechanistic Interpretability for End-to-End Self-Driving
Overview
This research applies mechanistic interpretability to end-to-end autonomous driving models by training Sparse Autoencoders (SAEs) on internal activations. The study reveals interpretable structures aligned with route intent, vehicle speed, and braking behavior, recovering route intent with 98.3% accuracy without supervision. Through counterfactual image edits, specific SAE features are shown to be visually grounded in scene changes like traffic light states and stop sign presence. Steering individual SAE latents produces predictable changes in planner outputs. A lightweight adapter trained on SAE latents reduces trajectory selection error by 3.44%, outperforming an equivalent adapter that omits SAE latents. Code and visualizations are available at https://mgagvani.github.io/mechanistic-interpretability-for-e2e-driving/.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported accuracy: 98.3 percent · Basis not reported
“retable structure aligned with route intent, vehicle speed, and braking behavior, recovering route intent with 98.3% accuracy without supervision. Through paired counterfactual image edits, we further show that specific SAE features are visually grounded and systematically respond to scene changes such as traffic light state and stop sign presence. Steering individual SAE latents produces predictable, monotonic chang”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalMechanistic Interpretability for End-to-End Self-Driving
This research applies mechanistic interpretability to end-to-end autonomous driving models by training Sparse Autoencoders (SAEs) on internal activations. The study reveals interpretable structures aligned with route intent, vehicle speed, and braking behavior, recovering route intent with 98.3% accuracy without supervision. Through counterfactual image edits, specific SAE features are shown to be visually grounded in scene changes like traffic light states and stop sign presence. Steering individual SAE latents produces predictable changes in planner outputs. A lightweight adapter trained on SAE latents reduces trajectory selection error by 3.44%, outperforming an equivalent adapter that omits SAE latents. Code and visualizations are available at https://mgagvani.github.io/mechanistic-interpretability-for-e2e-driving/.
Event coverage history
Current attention 9·Peak within the comparable range 10（2026-11-02 06:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).