INDEX

Explanations

news-related terms and developments

oai_token-act-pair · gpt-3.5-turbo

mentions of current news and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

lying

-0.77

lain

-0.76

emale

-0.68

Klu

-0.68

ifferent

-0.67

erving

-0.66

utical

-0.65

eder

-0.64

unction

-0.64

 Ended

-0.63

POSITIVE LOGITS

 installment

0.83

 arrivals

0.79

 imaginable

0.77

 developments

0.71

DragonMagazine

0.71

 incarnation

0.69

PH

0.65

Charges

0.64

 iteration

0.63

 refresh

0.63

Activations Density 0.102%

news-related terms and developments

mentions of current news and updates

No Comments

No Known Activations