INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

plex

-0.96

bered

-0.83

 Parables

-0.78

ional

-0.73

ffe

-0.70

rentice

-0.69

avorite

-0.68

istered

-0.67

 constrained

-0.66

Geh

-0.65

POSITIVE LOGITS

soDeliveryDate

0.84

NPR

0.81

UF

0.75

rats

0.75

ãĥĻ

0.72

Shipping

0.71

 looting

0.70

ucci

0.68

 captcha

0.67

UFC

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.