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

Not in Any Lists

No Comments

Negative Logits

apest

-0.74

soDeliveryDate

-0.73

awaru

-0.68

tions

-0.68

dds

-0.67

 printf

-0.64

azo

-0.64

 calcul

-0.62

itaire

-0.62

umbledore

-0.62

POSITIVE LOGITS

gran

0.72

thumbnails

0.67

frey

0.65

gor

0.64

ascar

0.64

ãĥ¼ãĥ³

0.63

Lago

0.63

senal

0.63

 stock

0.62

 Ventura

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.