conftrace_

neural network analysis

21 papers

Explore in graph

Co-occurring keywords

mechanistic interpretability (133) large language model (13587) neural network (6616) language model (4599) neuron analysis (32) factual knowledge (131) knowledge representation (301) representation learning (6206) community detection (276) network visualization (6)

Papers

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models EMNLP 2025
Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models ACL 2025
How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis EMNLP 2025
Inferring Functionality of Attention Heads from their Parameters ACL 2025
On Relation-Specific Neurons in Large Language Models EMNLP 2025
Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models COLING 2025
Inner Information Analysis Algorithm for Deep Neural Network based on Community ICLR 2025
Hypothesis Testing the Circuit Hypothesis in LLMs NIPS 2024
Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions CVPR 2024
Does Large Language Model Contain Task-Specific Neurons? EMNLP 2024
Transformer-specific Interpretability EACL 2024
Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars NIPS 2023
An Operator Theoretic Approach for Analyzing Sequence Neural Networks AAAI 2023
Evaluating Neuron Interpretation Methods of NLP Models NIPS 2023
Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision ICML 2023
Towards Automated Circuit Discovery for Mechanistic Interpretability NIPS 2023
An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks AAAI 2020
Analyzing Neural Discourse Coherence Models EMNLP 2020
Invariance of Weight Distributions in Rectified MLPs ICML 2018
Vectorial Semantic Spaces Do Not Encode Human Judgments of Intervention Similarity CONLL 2018
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks NIPS 2016