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

 rake

-0.69

 yield

-0.68

%%

-0.67

URI

-0.66

ª

-0.65

LOD

-0.63

rc

-0.62

FontSize

-0.60

exec

-0.59

ĪĴ

-0.59

POSITIVE LOGITS

anguage

0.74

idad

0.72

existence

0.71

otype

0.69

monton

0.67

opia

0.67

opic

0.66

Æ

0.66

shop

0.65

icultural

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.