Independent AI Research Lab

SINGULARITY LABS

Cracking how
LLMs think.

Singularity Labs is an independent research lab studying the inner world of language models — the representations, circuits, and dynamics behind how they reason. We work to make machine cognition legible.

OUTPUT 96  SEED: 3573860127 FIG.01 — CHILD / OPENING UNIVERSE
PLATE 01 RENDER · GRAYSCALE
Singularity Labs — a child gazing into an opening universe
OUTPUT 96  SEED: 3573860127 singularitylabs.love

01 Mission

Make machine cognition legible.

Understanding how a model thinks — not just what it outputs — is the foundation of AI that is safe, trustworthy, and genuinely capable. We pursue that understanding as a first-class scientific goal.

02 Research

What we study.

01

Mechanistic Interpretability

Reverse-engineering the circuits and features behind model behavior.

02

Reasoning & Cognition

How models plan, deliberate, abstract, and generalize.

03

Representation Geometry

The structure of latent space and what models encode.

04

Training Dynamics

How concepts and capabilities emerge over training.

FIELD · DITHERED GRADIENT OUTPUT 288  SEED: 2226809351

03 Collaborate

Work with us.

We collaborate with researchers and teams working on how models think.

info@singularitylabs.love

OUTPUT 317  SEED: 3396188657