INDEX

Explanations

the name "Nelson" appearing in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Nelson" and its significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

fare

-0.89

orical

-0.76

Â§

-0.74

-0.73

¾

-0.73

ãĤ¼

-0.71

orate

-0.70

place

-0.68

¿

-0.68

BOOK

-0.68

POSITIVE LOGITS

 Mandela

1.51

 Nelson

1.10

illo

0.85

sey

0.85

 Rockefeller

0.83

otine

0.82

elson

0.76

Sau

0.74

shire

0.70

stown

0.68

Activations Density 0.006%

the name "Nelson" appearing in various contexts

mentions of the name "Nelson" and its significance in various contexts

No Comments

No Known Activations