Patch-effect graphs built from causal mediation, partial correlation, and co-influence, when analyzed with graph kernels, preserve task-discriminative signals from activation patching that outperform global shape descriptors and raw baselines on GPT-2 Small.
Language models are unsupervised multitask learners.OpenAI Blog, 1(8):9
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Selective Neuron Amplification boosts task-relevant neurons during inference to improve uncertain outputs in language models.
Random label bridge training aligns LLM parameters with vision tasks, and partial training of certain layers often suffices due to their foundational properties.
citing papers explorer
-
Patch-Effect Graph Kernels for LLM Interpretability
Patch-effect graphs built from causal mediation, partial correlation, and co-influence, when analyzed with graph kernels, preserve task-discriminative signals from activation patching that outperform global shape descriptors and raw baselines on GPT-2 Small.
-
Selective Neuron Amplification in Transformer Language Models
Selective Neuron Amplification boosts task-relevant neurons during inference to improve uncertain outputs in language models.
-
Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
Random label bridge training aligns LLM parameters with vision tasks, and partial training of certain layers often suffices due to their foundational properties.