Uncategorized

• 3Blue1Brown: How might LLMs store facts | Chapter 7, Deep Learning
• ICML24: Physics of Language Models
• NAACL24: Explanations in the Era of Large Language Models
• 3Blue1Brown: But what is a GPT? Visual intro to transformers | Chapter 5, Deep Learning
• 3Blue1Brown: Attention in transformers, visually explained | Chapter 6, Deep Learning
• GitHub Repo stars - source-sparse-autoencoders-for-all-residual-stream))
• Github Repo stars
• GitHub Repo stars - chapter1-transformer-interp.streamlit.app/[1.2]_Intro_to_Mech_Interp), [Demo](https://colab.research.google.com/github/neelnanda-io/TransformerLens/blob/main/demos/Main_Demo.ipynb))
• GitHub Repo stars - team/nnsight): enables interpreting and manipulating the internals of deep learned models. ([Doc](https://nnsight.net/documentation/), [Tutorial](https://nnsight.net/tutorials/), [Paper](https://arxiv.org/abs/2407.14561))
• GitHub Repo stars
• GitHub Repo stars - tuning method. ([Paper](https://arxiv.org/pdf/2404.03592), [Demo](https://colab.research.google.com/github/stanfordnlp/pyreft/blob/main/main_demo.ipynb))
• GitHub Repo stars - engineering/))
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2
• GitHub Repo stars - eXplains-Transformers): Layer-wise Relevance Propagation (LRP) extended to handle attention layers in Large Language Models (LLMs) and Vision Transformers (ViTs). ([Paper](https://arxiv.org/pdf/2402.05602), [Doc](https://lxt.readthedocs.io/en/latest/))
• 200 Concrete Open Problems in Mechanistic Interpretability
• GitHub Repo stars - lens): Tools for understanding how transformer predictions are built layer-by-layer. ([Paper](https://arxiv.org/pdf/2303.08112), [Doc](https://tuned-lens.readthedocs.io/en/latest/))
• GitHub Repo stars - team/inseq): Pytorch-based toolkit for common post-hoc interpretability analyses of sequence generation models. ([Paper](http://arxiv.org/abs/2302.13942), [Doc](https://inseq.org/en/latest/))
• GitHub Repo stars - Abstract.html), [Doc](https://shap.readthedocs.io/en/latest/))
• GitHub Repo stars
• A Barebones Guide to Mechanistic Interpretability Prerequisites
• Concrete Steps to Get Started in Transformer Mechanistic Interpretability
• 3Blue1Brown: But what is a GPT? Visual intro to transformers | Chapter 5, Deep Learning
• 3Blue1Brown: Attention in transformers, visually explained | Chapter 6, Deep Learning
• GitHub Repo stars
• GitHub Repo stars - specific Interpretability](https://projects.illc.uva.nl/indeep/tutorial/) ([Github](https://github.com/interpretingdl/eacl2024_transformer_interpretability_tutorial))
• AI Alignment Forum
• LessWrong
• GitHub Repo stars - debugger): investigate specific behaviors of small LLMs
• GitHub Repo stars
• **Neuronpedia**
• **ML Alignment & Theory Scholars (MATS)**
• GitHub Repo stars - deepmind/penzai): a JAX library for writing models as legible, functional pytree data structures, along with tools for visualizing, modifying, and analyzing them. ([Paper](https://openreview.net/attachment?id=KVSgEXrMDH&name=pdf), [Doc](https://penzai.readthedocs.io/en/stable/), [Tutorial](https://penzai.readthedocs.io/en/stable/notebooks/how_to_think_in_penzai.html))
• Mechanistic Interpretability Workshop 2024 ICML - accept-oral))
• Attributing Model Behavior at Scale Workshop 2023 NeurIPS - accept-oral))
• BlackboxNLP 2023 EMNLP - 2023/#2023blackboxnlp-1))
• GitHub Repo stars