IAAR-Shanghai/Awesome-Attention-Heads

Issues

• Add new paper: Understanding Knowledge Hijack Mechanism in In-context Learning through Associative Memory

  #37 opened 11 days ago by wyzh0912
  0

• Add new paper: The Developmental Landscape of In-Context Learning

  #33 opened 12 days ago by wyzh0912
  0

• Add new paper: In-Context Language Learning: Architectures and Algorithms

  #32 opened 12 days ago by wyzh0912
  1

• Add new paper: Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

  #31 opened 12 days ago by wyzh0912
  0

• Add new paper: Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers

  #30 opened 12 days ago by wyzh0912
  0

• Add new paper: Memorization in Attention-only Transformers

  #29 opened 12 days ago by fan2goa1
  0

• Add new paper: Understanding Addition in Transformers

  #36 opened 12 days ago by wyzh0912
  0

• Add new paper: Algorithmic Phase Transitions in Language Models: A Mechanistic Case Study of Arithmetic

  #35 opened 12 days ago by wyzh0912
  0

• Add new paper: Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability

  #34 opened 12 days ago by fan2goa1
  0

• Add new paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs

  #27 opened 2 months ago by wyzh0912
  0

• Add new paper: Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models

  #28 opened 2 months ago by wyzh0912
  0

• Add new paper: Transformers on Markov Data: Constant Depth Suffices

  #24 opened 2 months ago by wyzh0912
  0

• Add new paper: Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics

  #23 opened 2 months ago by wyzh0912
  0

• Add new paper: Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers

  #25 opened 2 months ago by wyzh0912
  0

• Add new paper: How Transformers Learn Causal Structure with Gradient Descent

  #26 opened 2 months ago by wyzh0912
  0

• Add new paper: Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

  #21 opened 2 months ago by wyzh0912
  0

• Add new paper: A Psycholinguistic Evaluation of Language Models’ Sensitivity to Argument Roles

  #22 opened 2 months ago by wyzh0912
  0

• Add new paper: On the Role of Attention Heads in Large Language Model Safety

  #20 opened 2 months ago by wyzh0912
  0

• Add new paper: Round and Round We Go! What makes Rotary Positional Encodings useful?

  #16 opened 2 months ago by wyzh0912
  0

• Add new paper: The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling

  #17 opened 2 months ago by wyzh0912
  0

• Add new paper: DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

  #18 opened 2 months ago by wyzh0912
  0

• Add new paper: Locking Down the Finetuned LLMs Safety

  #19 opened 2 months ago by wyzh0912
  0

• Add new paper: How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning

  #15 opened 2 months ago by wyzh0912
  0

• Add new paper: Revisiting In-context Learning Inference Circuit in Large Language Models

  #14 opened 2 months ago by wyzh0912
  0

• Add new paper: Interpreting and Improving Large Language Models in Arithmetic Calculation

  #13 opened 2 months ago by wyzh0912
  0

• Add new paper: Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis

  #12 opened 2 months ago by fan2goa1
  0

• Might be a better form of presentation.

  #10 opened 4 months ago by Ki-Seki
  1

• New Heads To Add

  #2 opened 6 months ago by Ki-Seki
  2