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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

irgin

-0.73

 ILCS

-0.70

inventoryQuantity

-0.70

-0.69

bryce

-0.67

 Freddie

-0.67

Dialogue

-0.66

areth

-0.66

bed

-0.65

 millenn

-0.63

POSITIVE LOGITS

 Zoom

0.71

 Conc

0.70

âĢ¢âĢ¢

0.68

 Wolverine

0.64

gettable

0.64

 Aerospace

0.63

 remotely

0.63

Flight

0.62

 redesigned

0.62

collection

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.