Domain TopK sparse autoencoders trained on the residual stream of instruction-tuned LLMs while they read fact-checking verdict prompts (claim + evidence + instructions), released to study how models decide to abstain ("NOT ENOUGH EVIDENCE") instead of issuing a verdict. Off-the-shelf SAEs reconstruct the verdict-decision position poorly (it is out of their training distribution); these SAEs are trained on the task distribution itself, so the decision position is in-distribution. Training follows Gao et al. (2024) — see each SAE's card for the full configuration and metrics. Browse the latents in the SAE viewer: lucasfrag/fact-checking-abstention-saes-viewer (top-activating claims at the…
Independent publisher
Lucas Fraga
lucasfrag
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.