INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Comments

-0.72

microsoft

-0.71

 Siberian

-0.68

monton

-0.68

borgh

-0.68

isconsin

-0.67

 Amateur

-0.66

 Texans

-0.64

anny

-0.63

ļéĨĴ

-0.63

POSITIVE LOGITS

ortium

0.67

alled

0.66

minist

0.66

INS

0.63

grave

0.63

Chance

0.61

orthy

0.60

FG

0.59

NH

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.