conftrace_

activation vector

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model steering (1) transformer model (1) explanation representation (1) inference-time control (1) neural activation (1) activation steering (1) decoder model (1) faithful explanation (1) deep neural network (1) model interpretability (1)

Papers

Improving Instruction-Following in Language Models through Activation Steering ICLR 2025 InversionView: A General-Purpose Method for Reading Information from Neural Activations NeurIPS 2024 Locally Distributed Activation Vectors for Guided Feature Attribution COLING 2022