INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

inelli

-0.70

ggies

-0.66

antine

-0.65

essed

-0.62

intel

-0.61

onda

-0.61

ymes

-0.61

 JUSTICE

-0.61

ably

-0.58

 boxed

-0.58

POSITIVE LOGITS

enter

0.81

minecraft

0.74

will

0.73

isSpecialOrderable

0.73

 Rapids

0.71

 will

0.69

 enthusi

0.68

flows

0.66

venants

0.62

Will

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.