INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Chip

-0.80

 Paleo

-0.71

 Canaver

-0.70

Ħ¢

-0.66

cedented

-0.64

wered

-0.63

velt

-0.63

 Chip

-0.63

 constitu

-0.62

Parent

-0.61

POSITIVE LOGITS

 warr

0.80

uty

0.75

 royalty

0.65

landers

0.65

 Waste

0.63

 ugly

0.62

ools

0.61

 destiny

0.60

ury

0.60

ydia

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.