We've open-sourced our LLM attention visualization library
Inspectus allows you to create interactive visualizations of attention matrices with just a few lines of Python code. It’s designed to run smoothly in Jupyter notebooks through an easy-to-use Python API. Inspectus provides multiple views to help you understand language model behaviors. If you have any questions, feel free to ask!
We've open-sourced our LLM attention visualization library launched on June 9, 2024 with 197 votes, #231 of 4,672 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 2 years on.
In plain words
Inspectus is an open-source Python library for visualizing attention matrices from language models. It runs in Jupyter notebooks with a simple API that requires just a few lines of code. The tool offers multiple interactive views to help researchers and developers examine how attention mechanisms work in language models. It's designed for anyone working with LLMs who needs to understand model behavior through attention analysis.
written from the facts on this page · September 2026
From the sources
LLM Analytics. Contribute to labmlai/inspectus development by creating an account on GitHub.
Does a similar job
all alternatives →
Fully client-side GPT2 prediction visualizer2023 · perplexity.vercel.app · ▲153Hi HN! I've found this visualization tool immensely helpful over the years for getting an intuition for how an LLM "sees" some piece of text, and with a bit of elbow grease decided to move all compute to client side so I could make it publicly available. I've found it particularly useful for - Understanding exactly how repetition and patterns affect a small LM's ability to predict correctly - Understanding different tokenization patterns and how it affects model output - Getting a general sense of how "hard" different prediction tasks are for GPT-style models Known problems (that I probably…
LLM Attention VisualizationSep 2026 · ishamf.dev · ▲176I often need to convert times between time zones, so I built this tool to convert between them quickly and efficiently. 1. Add the cities you want to convert between (this is saved in the browser). 2. Drag on the map until the time on the source city is the time you want. 3. Look at the time at the other city. It's even more helpful to use on a phone since it doesn't require typing to convert between time zones or look up the time in another city (assuming you already added the cities you care about). If you need to convert a time far in the future, you can input the date and time in the…
ThoughtDAG – An editable context graph for LLM conversationsAug 2026 · chenxiachan.github.io · ▲136ThoughtDAG indexes local agent conversations across tools, finds the turns relevant to your work, and turns them into editable context graphs.
I Created ErisForge, a Python Library for Abliteration of LLMs2025 · github.com · ▲140ErisForge is a Python library designed to modify Large Language Models (LLMs) by applying transformations to their internal layers. Named after Eris, the goddess of strife and discord, ErisForge allows you to alter model behavior in a controlled manner, creating both ablated and augmented versions of LLMs that respond differently to specific types of input. It is also quite useful to perform studies on propaganda and bias in LLMs (planning to experiment with deepseek). Features - Modify internal layers of LLMs to produce altered behaviors. - Ablate or enhance model responses with the…
Ruby Heap Viz – An interactive Ruby object graph visualization2014 · github.com · ▲51An interactive Ruby Object Graph Visualization. Contribute to mattbaker/ruby-heap-viz development by creating an account on GitHub.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, June 2024
the whole month →
La Growth Machine▲1,216Create personalized, multi-channel conversations at scale
AI · 2024 · lagrowthmachine.com
PyjamaHR▲1,132Hiring on autopilot. The AI applicant tracking system (ATS).
Work · 2024 · pyjamahr.com