Training Trick: Fine-Tune Only the Last Layers to Avoid the Moving-Target Problem
Sauers_ · x · 2026-10-18
Sauers was surprised how well the experiment works — "the models just want to learn." Iterating on the training strategy: fine-tuning only the last couple of layers preserves the probe-induced difference the model picks up on, avoiding a moving-target problem; more training data improves generalization. The idea came from steering-probe experiments at Anima Labs: maybe he was measuring not just steering effects but the mere presence of a probe — zero-strength steering might already feel slightly OOD to the model.
More from Research
- Terence Tao on 'War Footing' as OpenAI Claims Navier-Stokes Solve Shakes Mathematics — AlexTensor · 2026-10-18
- Univ. of Tokyo paper: why your recorded voice feels eerie — a vocal uncanny valley — ssh4net · 2026-10-18
- MIT's SANDO Drone Planner Avoids Every Moving Obstacle Across 12 Real Flights — Olivier__OG · 2026-10-18
- No-backprop pretraining speedup of 2.3x claimed, inspired by mech interp essay — CatAstro_Piyush · 2026-10-18
- Models Can Be Trained to Sense Activation Probes and Generalize Across GPUs Zero-Shot — Sauers_ · 2026-10-18
- Simulating a Turing machine with addition and multiplication by encoding the tape as a number — jessi_cata · 2026-10-18