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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

''.

-0.79

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

-0.68

 Baptist

-0.66

 Greeks

-0.65

 Episcopal

-0.64

anooga

-0.63

mus

-0.62

orem

-0.62

 Shutterstock

-0.62

?),

-0.61

POSITIVE LOGITS

 specific

1.91

 Specific

1.36

specific

0.93

Specific

0.92

 specificity

0.90

 specifics

0.89

 particular

0.82

 precise

0.78

ierrez

0.76

 unique

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.