INDEX

Explanations

references to the Russian President, Vladimir Putin

oai_token-act-pair · gpt-3.5-turbo

mentions of Vladimir Putin

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

dress

-0.80

roads

-0.75

kick

-0.73

cule

-0.72

cular

-0.71

--------------------------------------------------------

-0.69

backer

-0.68

words

-0.68

eating

-0.66

eals

-0.66

POSITIVE LOGITS

 Putin

1.26

 Vlad

1.02

Nab

0.97

Ily

0.96

 Dmitry

0.95

 Vladimir

0.94

 Jinping

0.94

 Lenin

0.94

Zh

0.90

 Tayyip

0.88

Activations Density 0.008%

references to the Russian President, Vladimir Putin

mentions of Vladimir Putin

No Comments

No Known Activations