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

adian

-0.68

amental

-0.68

 footing

-0.66

bered

-0.65

hett

-0.64

obiles

-0.64

items

-0.63

dict

-0.63

 offenses

-0.63

oby

-0.63

POSITIVE LOGITS

pora

0.87

£ı

0.73

 Journalism

0.73

aida

0.72

 Tuls

0.72

acus

0.70

NSA

0.70

 Murdoch

0.69

 Morg

0.68

çīĪ

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.