INDEX

Explanations

phrases related to statistical data and scientific findings

oai_token-act-pair · gpt-3.5-turbo

statements involving comparative statistics or relationships between variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

soon

-0.67

usa

-0.67

reader

-0.66

DragonMagazine

-0.66

asha

-0.66

eday

-0.63

umn

-0.63

 Debor

-0.62

ourney

-0.61

atching

-0.61

POSITIVE LOGITS

 higher

1.45

 fewer

1.37

 lower

1.33

 greater

1.33

 poorer

1.31

 superior

1.26

 stronger

1.25

higher

1.20

 weaker

1.19

 decreased

1.16

Activations Density 0.323%

phrases related to statistical data and scientific findings

statements involving comparative statistics or relationships between variables

No Comments

No Known Activations