INDEX

Explanations

mentions of the name "Nelson Mandela."

oai_token-act-pair · gpt-3.5-turbo

references to Nelson Mandela

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

-0.79

payers

-0.70

mble

-0.69

CBI

-0.68

VALUE

-0.66

orate

-0.65

orically

-0.63

place

-0.63

teenth

-0.62

ãĤ¼

-0.62

POSITIVE LOGITS

 Mandela

1.67

 Rockefeller

0.87

illo

0.87

 Nelson

0.86

otine

0.81

sey

0.80

shire

0.79

essa

0.77

elson

0.75

Sau

0.71

Activations Density 0.041%

mentions of the name "Nelson Mandela."

references to Nelson Mandela

No Comments

No Known Activations