Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.
-
Updated
Apr 22, 2025 - Jupyter Notebook
#
transformerlens
Here are 10 public repositories matching this topic...
[NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching"
language-model circuit-analysis interpretability explainable-ai interpretable-machine-learning explainability llms mechanistic-interpretability transformerlens neurips-2025
-
Updated
Nov 3, 2025 - Python
Lightweight representation engineering dataflow operations for agent developers.
transformers pytorch dataflow parquet huggingface huggingface-transformers duckdb pylance mechanistic-interpretability lancedb transformerlens representation-engineering pragmatic-interpretability
-
Updated
Dec 18, 2025 - Python
Implementation and analysis of Sparse Autoencoders for neural network interpretability research. Features interactive visualization dashboard and W&B integration.
sparse-autoencoders interpretability activation-functions neuron-activity wandb transformerlens mech-interp
-
Updated
Nov 21, 2025 - Python
Investigating whether language models encode anticipated social consequences in their activations. Uses a 2x2 factorial design crossing truth × social valence to show that models are more sensitive to expected approval/disapproval than to truth itself.
language-models ai-safety interpretability deception-detection mechanistic-interpretability transformerlens
-
Updated
Dec 18, 2025 - Python
Training and exploration of linear probes into Othello-GPT by Li et al. (2022)
-
Updated
Jun 29, 2023 - Jupyter Notebook
Testing role-based pathways on small LLMs
research transformers pytorch ai-safety interpretability attention-mechanisms ai-alignment llm mechanistic-interpretability transformerlens
-
Updated
Dec 11, 2025 - Python
A Flax-based library for examining transformers, based on TransformerLens.
-
Updated
Feb 11, 2024 - Python
Reverse engineering the circuit responsible for the "greater than" capability in a language model
attention-mechanism ablation-studies mechanistic-interpretability transformerlens activation-patterns gpt-2-small
-
Updated
Oct 14, 2025 - Python
(a1)Mechanistic Interpretability using Transformer Lens (a2) PEFT
-
Updated
Sep 3, 2025 - Jupyter Notebook
Improve this page
Add a description, image, and links to the transformerlens topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the transformerlens topic, visit your repo's landing page and select "manage topics."