INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ailability

-0.80

ĪĴ

-0.73

pmwiki

-0.70

æ©

-0.68

-0.65

ILLE

-0.64

 appellate

-0.63

00200000

-0.62

rid

-0.61

 uncertain

-0.61

POSITIVE LOGITS

adia

0.71

 Congratulations

0.70

 kidding

0.69

 Adin

0.64

HIM

0.64

Congratulations

0.62

Di

0.61

velt

0.61

Zi

0.61

$$

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.