INDEX

Explanations

mentions of the city of Paris

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Meille

-0.78

 Foire

-0.77

 Mère

-0.75

 Aéroport

-0.74

Théâtre

-0.73

 buhay

-0.69

 Meilleur

-0.69

Probl

-0.69

 tanong

-0.67

 Photographie

-0.67

POSITIVE LOGITS

 Paris

1.39

Paris

1.31

 PARIS

1.30

 impra

1.26

 increa

1.25

 uninten

1.25

 paris

1.23

 affor

1.22

 maneu

1.21

 erad

1.20

Activations Density 0.042%

mentions of the city of Paris

No Comments

No Known Activations