INDEX

Explanations

references to the word "Pra" or related terms, indicating a focus on "Prairies" or geographical regions in Canada

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cammino

-0.80

 GEOLOGY

-0.75

 tört

-0.73

 desnuda

-0.73

 mulighed

-0.72

 laim

-0.71

 DISEASES

-0.70

Dzięki

-0.70

/**

-0.69

Wię

-0.68

POSITIVE LOGITS

 prouve

1.12

Pes

1.11

Pra

1.06

Pra

1.06

Pes

1.05

Tal

1.04

 illustre

0.96

 exé

0.96

Tal

0.94

 trouvera

0.91

Activations Density 0.157%

references to the word "Pra" or related terms, indicating a focus on "Prairies" or geographical regions in Canada

No Comments

No Known Activations