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

 Conquer

-0.82

uckland

-0.71

 organis

-0.68

 Tempest

-0.66

=~=~

-0.65

ards

-0.64

 legislator

-0.62

sted

-0.62

 organisers

-0.61

 suscept

-0.61

POSITIVE LOGITS

ky

1.20

first

0.79

$_

0.71

ueller

0.70

current

0.70

catentry

0.69

traditional

0.68

sky

0.67

espie

0.66

owan

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.