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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RI

-0.74

gel

-0.71

IU

-0.70

owner

-0.69

RM

-0.69

WR

-0.67

 GDDR

-0.67

rix

-0.65

EA

-0.65

RAW

-0.65

POSITIVE LOGITS

 Christmas

1.68

Christmas

1.39

 children

0.93

children

0.83

Children

0.79

 Christensen

0.79

 kids

0.74

ussen

0.72

 Children

0.71

child

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.