INDEX

Explanations

large quantities or numbers of people, items, or entities mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

odox

-0.71

imaru

-0.61

Leader

-0.60

 precedence

-0.60

 srfAttach

-0.58

SourceFile

-0.58

 Ratt

-0.57

 rapport

-0.57

 Apocalypse

-0.56

ç·

-0.56

POSITIVE LOGITS

 worldwide

1.28

 annually

1.20

 globally

1.04

 nationwide

0.99

 apiece

0.83

abytes

0.80

 across

0.77

 crore

0.75

 total

0.75

 crammed

0.75

Activations Density 0.289%

large quantities or numbers of people, items, or entities mentioned in the text

No Comments

No Known Activations