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

JD

-0.75

Fly

-0.73

 retri

-0.71

HOU

-0.69

 traveller

-0.69

 pige

-0.67

 Airbus

-0.67

LIA

-0.66

ADS

-0.66

ircraft

-0.66

POSITIVE LOGITS

uch

1.67

atism

0.75

ita

0.67

inky

0.67

 punished

0.66

apon

0.63

itas

0.63

ogie

0.62

 imprint

0.62

Gab

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.