© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

CIRCUITGPT-PYTHON · 2-MLP · 5534 ｜ Neuronpedia

Home
OpenAI · Weight-Sparse Transformers
CircuitGPT-Python
MLP
2-MLP
5534

INDEX

Circuit Sparsity

No connected neurons data available

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

if

-0.11

essage

-0.04

dividual

-0.04

ch

-0.04

odel

-0.03

arent

-0.03

isited

-0.03

visited

-0.03

rom

-0.02

li

-0.02

POSITIVE LOGITS

 colle

0.19

ome

0.13

den

0.06

ies

0.04

0.03

0.03

0.02

0.02

0.01

<extra_output_id:2047>

0.01

Activations Density 11.346%

No Known Activations