INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

phies

-0.86

£ı

-0.79

merce

-0.77

ructose

-0.75

ģ«

-0.75

ĸļ

-0.74

 leagues

-0.73

Cry

-0.72

EngineDebug

-0.72

agements

-0.72

POSITIVE LOGITS

 Macedonia

0.72

utenberg

0.70

 Denis

0.64

 populist

0.64

Uk

0.64

 Romania

0.62

ichick

0.62

 Albania

0.61

Os

0.61

inelli

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.