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

 Cance

-0.79

 Croatian

-0.64

 Gorge

-0.63

 Strawberry

-0.60

 Kurt

-0.60

Bub

-0.60

 Complete

-0.60

å°Ĩ

-0.59

Ruk

-0.59

Ob

-0.59

POSITIVE LOGITS

ebook

0.84

ife

0.80

isher

0.78

eely

0.76

idges

0.73

ICE

0.72

0.71

herer

0.71

IFE

0.70

Ware

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.