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

EY

-0.70

 categ

-0.67

ĸļ

-0.67

erial

-0.65

«ĺ

-0.63

ascript

-0.63

¥ŀ

-0.63

TIT

-0.62

 millenn

-0.62

 surpr

-0.61

POSITIVE LOGITS

espie

0.74

cause

0.71

advertising

0.68

ipedia

0.66

soDeliveryDate

0.64

 Pengu

0.62

á

0.62

effic

0.61

olini

0.61

acus

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.