No article text was recorded for this version.
embedding interpretability (representation interpretability)
Version 2 of 2612 papers672 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Semantic Structure and Interpretability of Word Embeddings
- Blog: Towards Interpretable Scientific Foundation Models: Sparse Autoencoders for Disentangling Dense Embeddings of Scientific Concepts
- Blog: Context Vectors are Reflections of Word Vectors in Half the Dimensions
- Blog: Rotated Word Vector Representations and their Interpretability
- Blog: Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
- Blog: Learning Effective and Interpretable Semantic Models using Non-Negative Sparse Embedding
- Blog: Toward an Integrative Approach for Making Sense Distinctions
- Blog: Changing the Basis of Contextual Representations with Explicit Semantics
- Blog: Compositional Fusion of Signals in Data Embedding
- Blog: Embedding Projector: Interactive Visualization and Interpretation of Embeddings
- Blog: Definition Frames: Using Definitions for Hybrid Concept Representations
- Blog: Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
- Blog: Sparse Word Embeddings Using
- Blog: EVE: explainable vector based embedding technique using Wikipedia
- Blog: Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models
- Blog: Understanding the Semantic Content of Sparse Word Embeddings Using a Commonsense Knowledge Base
- Blog: Improving Interpretability of Lexical Semantic Change with Neurobiological Features
- Blog: STAIR: Learning Sparse Text and Image Representation in Grounded Tokens
- Blog: EmbeddingTree: Hierarchical Exploration of Entity Features in Embedding
- Blog: Interpretable Word Embeddings via Informative Priors
- Blog: Representing ELMo embeddings as two-dimensional text online
- Blog: CNNs for NLP in the Browser: Client-Side Deployment and Visualization Opportunities
- Blog: The Expressive Power of Word Embeddings
- Blog: Online Learning of Interpretable Word Embeddings
- Blog: Neural Vector Conceptualization for Word Vector Space Interpretation
- Blog: A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces
- Blog: SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection
- Blog: Identification, Interpretability, and Bayesian Word Embeddings
- Blog: Semeval-2022 Task 1: CODWOE - Comparing Dictionaries and Word Embeddings
- Blog: Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
- Blog: Semantic Geometry of Sentence Embeddings
- Blog: STAIR: Learning Sparse Text and Image Representation in Grounded Tokens
- Blog: SLICE: Supersense-based Lightweight Interpretable Contextual Embeddings
- Blog: SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection
- Blog: Representation Learning for Natural Language Processing
- Blog: DASFAA 20202 Special Issue Editorial
- Blog: Independent Components of Word Embeddings Represent Semantic Features
- Blog: Definition Modeling: Learning to Define Word Embeddings in Natural Language
- Blog: Conditional Generators of Words Definitions
- Blog: Emerging Language Spaces Learned From Massively Multilingual Corpora
- Blog: Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding
- Blog: JoBimViz: A Web-based Visualization for Graph-based Distributional Semantic Models
- Blog: Word embeddings quantify 100 years of gender and ethnic stereotypes
- Blog: Building Lexical Vector Representations from Concept Definitions
- Blog: Learning linear transformations between counting-based and prediction-based word embeddings
- Blog: Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors
- Blog: Discovering Universal Geometry in Embeddings with ICA
- Blog: Are Fictional Voices Distinguishable? Classifying Character Voices in Modern Drama
- Blog: Multimodal Neurons in Pretrained Text-Only Transformers
- Blog: Knowledge Semantic Representation: A Generative Model for Interpretable Knowledge Graph Embedding
- Blog: Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification
- Blog: Survey on Multi-Output Learning
- Blog: Probing the Embedding Space of Protein Foundation Models through Intrinsic Dimension Analysis
- Blog: Disentangling language change: sparse autoencoders quantify the semantic evolution of indigeneity in French
- Blog: Hierarchical Retrieval at Scale: Bridging Interpretability and Efficiency
- Blog: Explaining Datasets in Words: Statistical Models with Natural Language Parameters
- Blog: Probe-Less Probing of BERT's Layer-Wise Linguistic Knowledge with Masked Word Prediction
- Blog: pix2rule: End-to-end Neuro-symbolic Rule Learning
- Blog: Automatically Generated Definitions and their utility for Modeling Word Meaning
- Blog: A case for deep learning in semantics
Showing 60 of 612 papers.
History & citation
Current · Permanent link
- Topographic Component Ordering via Traveling Salesman Optimization merged into this direction (50% overlap)
- Decomposing Latent Embeddings into Sparse Semantic Atoms merged into this direction (50% overlap)
- sparsity for interpretability split from this direction (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_embedding_interpretability_representatio_4d4f4acf,
title = {embedding interpretability (representation interpretability)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/embedding-interpretability-representation-interpretability/rdr_4d4f4acf3e7e4b809e4d978f315a8c71},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_embedding_interpretability_representatio_4d4f4acf_v2,
title = {embedding interpretability (representation interpretability)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/embedding-interpretability-representation-interpretability/rdr_4d4f4acf3e7e4b809e4d978f315a8c71/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}