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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Siberian

-0.75

 Siberia

-0.74

oki

-0.66

undai

-0.64

 Hiroshima

-0.63

 Suzuki

-0.63

 sedan

-0.63

 Mazda

-0.63

 Aman

-0.61

 influencing

-0.60

POSITIVE LOGITS

DL

0.79

yip

0.77

hew

0.76

inus

0.73

corn

0.73

 Brist

0.71

 Tags

0.70

Serv

0.69

eworthy

0.69

zzle

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.