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

roit

-0.71

Corp

-0.69

fleet

-0.68

Master

-0.66

orno

-0.65

ways

-0.63

 Kingdoms

-0.63

Â¶

-0.62

Company

-0.62

minist

-0.62

POSITIVE LOGITS

SPONSORED

0.87

 emulate

0.75

ppings

0.75

 fill

0.71

 replace

0.68

 weigh

0.67

 populate

0.67

 appre

0.66

 bolster

0.66

 breed

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.