Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Stress-Testing Random-Vector Controls for Activation Steering

AbstractRandom-vector controls provide a reference for interpreting activation-steering effects, but a single realization hides variation in that reference. We examine this variation and two separate implementation checks. In a released activation-addition (ActAdd) configuration on GPT-2-XL, we reproduce the steering arm over 57 prompts with a maximum absolute error of 1.74 × 10⁻⁶. At coefficient 10, 9 of 20 fresh random-control realizations have greater mean normalized Kullback–Leibler (KL) divergence than the steering arm, and 19 have lower means than the stored random realization. In a separate four-model study over 96 prompts, changing batch size or attention implementation changes the greedy next token for at most 5 and 6 prompts, respectively; an identical rerun changes none. Finally, an erroneous left-padding index in our own analysis pipeline, shared by the intervention and readout, overstates the maximum greedy-token change rate in 10 of 12 model-dose settings, with a median relative distortion of 46.8%. These findings support reporting realization-level variation, measuring configuration sensitivity, and validating intervention and readout indices. The results concern distributional change in the evaluated configurations, not semantic steering success.

More from EMNLP 2026

All EMNLP 2026 papers →