conftrace_

residual stream

30 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (10) mechanistic interpretability (6) attention head (6) sparse autoencoder (5) language model (3) hidden state (3) representation learning (3) jailbreak defense (2) activation steering (2) causal intervention (2)

Papers

Steering Llama 2 via Contrastive Activation Addition ACL 2024 Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models NeurIPS 2024 Transformers Represent Belief State Geometry in their Residual Stream NeurIPS 2024 A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis EMNLP 2023 Temporal Deformable Residual Networks for Action Segmentation in Videos CVPR 2018