© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

CIRCUITGPT-PYTHON · 2-MLP · 5928 ｜ Neuronpedia

Home
OpenAI · Weight-Sparse Transformers
CircuitGPT-Python
MLP
2-MLP
5928

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

 continue

-0.11

ast

-0.08

-0.07

-0.06

 return

-0.05

arg

-0.05

prese

-0.05

-0.05

.add

-0.04

 Returns

-0.04

POSITIVE LOGITS

 Calculate

0.08

etween

0.07

0.06

abs

0.05

0.05

ta

0.05

0.04

0.04

 math

0.04

0.04

Activations Density 58.673%

No Known Activations