👋 Aligning Human & Machine Vision using explainability

LENS Project

ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).

Sparse autoencoders for vision

Genome modeling and design across all domains of life

[ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models

This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking".

Sparsify transformers with SAEs and transcoders

Code for "The Geometry of Concepts: Sparse Autoencoder Feature Structure"

Developing Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography

Biological foundation modeling from molecular to genome scale

Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.

[NAACL 2025 Oral] From redundancy to relevance: Enhancing explainability in multimodal large language models

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

The nnsight package enables interpreting and manipulating the internals of deep learned models.

A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

This repository collects all relevant resources about interpretability in LLMs

A library for mechanistic interpretability of GPT-style language models

Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

👶🏻 신입 개발자 전공 지식 & 기술 면접 백과사전 📖

Official code and dataset for our paper: Intriguing Properties of Large Language and Vision Models