No article text was recorded for this version.
attention-centric interpretability bias
Version 1 of 124 papers28 conceptsfrozen 2026-10-04
Papers in this version
- Blog: AttCAT: Explaining Transformers via Attentive Class Activation Tokens
- Blog: Influence Patterns for Explaining Information Flow in BERT
- Blog: Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps
- Blog: Explainability of vision transformers: a comprehensive review and new perspectives
- Blog: Attention is Not Only a Weight: Analyzing Transformers with Vector Norms
- Blog: Holistically Explainable Vision Transformers
- Blog: How to Dissect a Muppet: The Structure of Transformer Embedding Spaces
- Blog: Dissecting Query-Key Interaction in Vision Transformers
- Blog: SANVis: Visual Analytics for Understanding Self-Attention Networks
- Blog: Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
- Blog: Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention
- Blog: Quantifying Attention Flow in Transformers
- Blog: Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
- Blog: Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
- Blog: Explaining ViTs Using Information Flow
- Blog: GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
- Blog: Extracting Rule-based Descriptions of Attention Features in Transformers
- Blog: Interpreting vision transformers via residual replacement model
- Blog: Discovering Influential Neuron Path in Vision Transformers
- Blog: Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention
- Blog: (Un)interpretability of Transformers: a case study with Dyck grammars
- Blog: Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
- Blog: Beyond Intuition: Rethinking Token Attributions inside Transformers
- Blog: Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_attention_centric_interpretability_bias_b2a4c48e,
title = {attention-centric interpretability bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/attention-centric-interpretability-bias/rdr_b2a4c48e7ddc44c8855f92117758a6d5},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_attention_centric_interpretability_bias_b2a4c48e_v1,
title = {attention-centric interpretability bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/attention-centric-interpretability-bias/rdr_b2a4c48e7ddc44c8855f92117758a6d5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}