INDEX

Explanations

phrases related to being at the center of something

oai_token-act-pair · gpt-3.5-turbo

references to central locations or pivotal concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥīãĥ©

-0.80

apons

-0.78

IELD

-0.72

ugg

-0.67

 Shotgun

-0.67

phies

-0.66

apon

-0.65

rentices

-0.64

areth

-0.64

IGHTS

-0.63

POSITIVE LOGITS

pieces

1.05

stadt

0.89

most

0.86

burst

0.81

piece

0.79

point

0.79

tenance

0.77

eous

0.75

fold

0.75

uve

0.75

Activations Density 0.015%

phrases related to being at the center of something

references to central locations or pivotal concepts

No Comments

No Known Activations