====== Visualizing Neural Networks ======
  * [[https://arxiv.org/pdf/1506.02078.pdf|Karpathy et al 2015 - Visualizing and Understanding Recurrent Networks]]
  * [[https://arxiv.org/pdf/1606.07461.pdf|Strobelt et al 2016 - LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks]] [[http://lstm.seas.harvard.edu/|demo]]
  * (Also the Transformer visualization demos at ACL 2020)
  * [[https://arxiv.org/pdf/2008.05122.pdf|Tenney et al 2020 - The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Model]]
  * [[https://arxiv.org/pdf/2310.03686|Langedijk et al 2023 - DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers]]

===== Software =====
  * [[https://github.com/jessevig/bertviz|BERTViz]] Zekun used.  Works in Colab.
  * LSTMViz (great)

===== Related Pages =====
  * [[nlp:Explainability]]
  * [[nlp:Probing Experiments]]