INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Downloadha

-0.81

BRE

-0.75

âĸĳ

-0.72

é¾įå¥ĳå£«

-0.69

çļ

-0.66

Oracle

-0.65

WARNING

-0.64

hess

-0.64

Gameplay

-0.63

Leave

-0.63

POSITIVE LOGITS

outheast

0.81

 hemisphere

0.80

asso

0.74

ertation

0.74

inav

0.70

izoph

0.68

sembly

0.67

ukong

0.67

iatrics

0.67

emis

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.