thinker
active
thinker:ryan-panwar

Ryan Panwar

Authored
1
Introduces
0
Studies
0
Affiliations
0
Cited by
1

Authored papers (1)

  • Interpretability can audit a preference dataset before optimization and predict what DPO will teach a model: on Dolci, clustering SAE features and testing chosen-minus-rejected activation differences predicted post-DPO feature shifts with R²=0.9 (feature-conditioned) and R²=0.58 (prompt-conditioned). The method is a two-view hypothesis-generation pipeline. A BatchTopK SAE on Llama-3.1-8B supplies the feature clusters (814 response-feature clusters, 512 data clusters over 259,842 pairs), and Welch tests with split-half sign-consistency filtering rank which concepts the labels reward. The pipeline flags Dolci DPO as teaching compliance with unsafe queries, and benchmarks such as HarmBench and XSTest confirm degraded safeguards after DPO. It also flags physics sycophancy, questionable fanfiction, benchmark recognition and hallucinated URLs. Four interventions (data filtering, inoculation prompting, activation steering, reward shaping) are unified as 'explaining away' a concept from an exponential tilt of the policy. Reward shaping is the strongest: at λ=−5 it cuts Llama-3.1-8B harmful-response rate from 21.7% to 4.0% while keeping OLMES accuracy near DPO's 0.434 (0.425), and it also amplifies traits such as playfulness. Interventions fail when the target concept is entangled with others or sparse in the data: style attributes leak off-target, and only URL hallucination improved significantly. The paper argues that post-training should treat the dataset as something to audit and the reward as something to sculpt, and that future protocols need concept hierarchies rather than flat, independent concept axes.

More papers — OpenAlex / S2

Co-authors (12)