INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Paraly

-0.73

castle

-0.68

 impe

-0.67

iken

-0.63

 embryo

-0.63

egg

-0.62

 Simmons

-0.62

vine

-0.62

inea

-0.62

 Rider

-0.61

POSITIVE LOGITS

Unix

0.76

manship

0.74

bies

0.71

Digital

0.70

Shipping

0.67

Fan

0.66

por

0.65

upon

0.65

arr

0.64

Hardware

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.