INDEX

Explanations

proper nouns, specifically names of historical or notable figures or places

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MpServer

-0.65

english

-0.64

rawdownloadcloneembedreportprint

-0.64

Cover

-0.64

enture

-0.63

ciplinary

-0.63

Online

-0.62

itely

-0.61

 independ

-0.61

OUND

-0.61

POSITIVE LOGITS

 Ezra

1.05

 Pierre

1.01

 Andrew

1.01

 Julius

0.99

 Rupert

0.97

 Richard

0.96

 Boris

0.95

 Peter

0.95

 JosÃ©

0.95

 Viktor

0.94

Activations Density 0.287%

proper nouns, specifically names of historical or notable figures or places

No Comments

No Known Activations