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

itars

-0.78

ecycle

-0.78

 Disciple

-0.76

>]

-0.72

recated

-0.72

liter

-0.71

å£«

-0.71

vest

-0.71

cery

-0.70

 Mahjong

-0.69

POSITIVE LOGITS

ogan

0.75

 Bett

0.67

 yawn

0.66

 conclud

0.65

bum

0.65

Sense

0.64

ASA

0.64

PN

0.63

AGES

0.62

asper

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.