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

terness

-0.78

empt

-0.74

ussion

-0.74

aj

-0.71

shut

-0.69

etheless

-0.67

utor

-0.67

requisite

-0.67

println

-0.65

iss

-0.65

POSITIVE LOGITS

 living

1.56

 live

1.44

 Live

1.39

 Living

1.26

Live

1.24

living

1.20

Living

1.15

 LIVE

1.13

 lived

1.08

live

0.96

Activations Density 0.000%

No Known Activations

This feature has no known activations.