INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

obb

-0.70

arb

-0.70

anton

-0.70

VERTIS

-0.67

vertising

-0.66

aud

-0.66

aughlin

-0.63

urch

-0.63

 unspecified

-0.63

obby

-0.62

POSITIVE LOGITS

xual

0.85

enegger

0.73

perture

0.72

Rue

0.71

ÃŁ

0.69

acea

0.67

Ame

0.67

 Nasa

0.66

ories

0.65

arers

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.