conftrace_

mechanistic interpretability

133 papers

Explore in graph

Also known as

MI

Co-occurring keywords

large language model (13587) language model (4599) sparse autoencoder (112) attention head (146) neural network (6616) circuit analysis (17) in-context learning (1405) circuit discovery (14) attention mechanism (4001) activation patching (23)

Papers

Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning IJCNLP 2025
From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs NAACL 2025
Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning NAACL 2025
RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs ACL 2025
Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification ACL 2025
Understanding Verbatim Memorization in LLMs Through Circuit Discovery ACL 2025
Racing Thoughts: Explaining Contextualization Errors in Large Language Models NAACL 2025
Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25 EMNLP 2025
From Parameters to Performance: A Data-Driven Study on LLM Structure and Development EMNLP 2025
Toward Efficient Sparse Autoencoder-Guided Steering for Improved In-Context Learning in Large Language Models EMNLP 2025
All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens EMNLP 2025
Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing EMNLP 2025
Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability CVPR 2025
Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference AAAI 2025
Benchmarking and Understanding Compositional Relational Reasoning of LLMs AAAI 2025
Unraveling the Influence of Training Data and Internal Structures in Large Language Models for Enhanced Explainability (Student Abstract) AAAI 2025
Language Models Encode the Value of Numbers Linearly COLING 2025
Computation Mechanism Behind LLM Position Generalization ACL 2025
Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors EMNLP 2025
How do autoregressive transformers solve full addition? EMNLP 2025
LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder EMNLP 2025
Isolating Culture Neurons in Multilingual Large Language Models AACL 2025
Pre-trained Large Language Models Use Fourier Features to Compute Addition NIPS 2024
Transcoders find interpretable LLM feature circuits NIPS 2024
On Large Language Models’ Hallucination with Regard to Known Facts NAACL 2024