Mudith Jayasekara

Charles O'Neill, Slava Chalnev, Chi Chi Zhao et al.

Contextual hallucinations -- statements unsupported by given context -- remain a significant challenge in AI. We demonstrate a practical interpretability insight: a generator-agnostic observer model detects hallucinations via a single forward pass and a linear probe on its residual stream. This probe isolates a single, transferable linear direction separating hallucinated from faithful text, outperforming baselines by 5-27 points and showing robust mid-layer performance across Gemma-2 models (2B to 27B). Gradient-times-activation localises this signal to sparse, late-layer MLP activity. Critically, manipulating this direction causally steers generator hallucination rates, proving its actionability. Our results offer novel evidence of internal, low-dimensional hallucination tracking linked to specific MLP sub-circuits, exploitable for detection and mitigation. We release the 2000-example ContraTales benchmark for realistic assessment of such solutions.

Charles O'Neill, Mudith Jayasekara, Max Kirkby

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only high-frequency, generic patterns. This often results in significant linear ``dark matter'' in reconstruction error and produces latents that fragment or absorb each other, complicating interpretation. We show that restricting SAE training to a well-defined domain (medical text) reallocates capacity to domain-specific features, improving both reconstruction fidelity and interpretability. Training JumpReLU SAEs on layer-20 activations of Gemma-2 models using 195k clinical QA examples, we find that domain-confined SAEs explain up to 20\% more variance, achieve higher loss recovery, and reduce linear residual error compared to broad-domain SAEs. Automated and human evaluations confirm that learned features align with clinically meaningful concepts (e.g., ``taste sensations'' or ``infectious mononucleosis''), rather than frequent but uninformative tokens. These domain-specific SAEs capture relevant linear structure, leaving a smaller, more purely nonlinear residual. We conclude that domain-confinement mitigates key limitations of broad-domain SAEs, enabling more complete and interpretable latent decompositions, and suggesting the field may need to question ``foundation-model'' scaling for general-purpose SAEs.