INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

UA

-0.78

RA

-0.73

 Truth

-0.71

Berry

-0.71

EW

-0.68

-0.66

 Honest

-0.65

enburg

-0.65

ECK

-0.64

oday

-0.63

POSITIVE LOGITS

izoph

0.78

 mosqu

0.73

uador

0.72

 fitt

0.69

 incre

0.69

 afore

0.69

yip

0.68

à¥

0.65

 Azerb

0.65

duino

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.