Superposition and Dictionary Learning Features
November 7, 2026
No Comments
When features are sparse, superposition is the phenomenon of representing more features than there are dimensions.
AI interpretability · Jacobian Lens · alignment
How language models think — made legible.
Research explainers on J-Space and the internal workspaces where modern LLMs stage reportable reasoning.
Featured · AI Safety
Safety teams decode models with mechanistic interpretability
How safety teams use interpretability to catch behaviors that tests miss — and make model behavior operational.
Read featured explainer →All explainers
Deep dives on Anthropic’s interpretability work, internal workspaces in LLMs, and what J-Space reveals about model behavior.
Neuron Transfer Functions Inside Circuits
November 5, 2026
No Comments
A 2024 arXiv preprint frames neuron-to-neuron computation as transfer functions, clarifying what circuit analysis can claim about language models.
Rosetta Neurons Scaling Paper Review
November 2, 2026
No Comments
Rosetta Neurons scaling paper review: shared neurons in 80M-30B parameter models grow as a sublinear power law (exponent 0.5-0.7), so their share falls.
Access Tests Are Not Phenomenal Consciousness
November 1, 2026
No Comments
The definition that answers the first part of the question is in the section “What about consciousness?”
Arithmetic Patching Paper: GN vs STR
October 31, 2026
No Comments
GN on the arithmetic prompts adds Gaussian noise to the token embeddings of the third example’s operands, X 3 and Y 3.
Vision Sparse Autoencoder L0
October 29, 2026
No Comments
That expression formalizes the prose definition. The PDF text used here does not display this equation.
A research lens on internal model cognition
J-Space tracks the sparse internal workspace where language models stage reportable reasoning. The Jacobian Lens makes that workspace measurable — so safety, alignment, and interpretability research can move from speculation to evidence.