2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Overall, the results show that targeted feature quality depends jointly on the model signal and estimator, with detection and intervention capturing complementary properties.
We present gradiend, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation, training, evaluation, visualization, persistent mod...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
