INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

FactoryReloaded

-0.76

xp

-0.75

Beck

-0.74

hao

-0.74

patient

-0.69

illary

-0.69

 Reasons

-0.68

irtual

-0.67

ilial

-0.67

oa

-0.65

POSITIVE LOGITS

Sud

0.68

 Soviets

0.65

 theirs

0.64

cin

0.63

whelming

0.63

),"

0.62

olson

0.61

Oss

0.61

 unsafe

0.61

 empt

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.