INDEX

Explanations

phrases expressing opinions or reflections on societal issues, particularly related to media and journalism

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

xodo

-0.56

zeciw

-0.52

 băr

-0.51

ével

-0.50

)._

-0.49

éhez

-0.48

 oamenii

-0.48

 femei

-0.47

);"

-0.47

בודה

-0.47

POSITIVE LOGITS

 lele

0.86

 saar

0.82

 mezza

0.79

 Khart

0.78

 Karang

0.78

 territo

0.78

 Ordre

0.74

umo

0.73

 Afgan

0.73

 lemp

0.72

Activations Density 0.306%

phrases expressing opinions or reflections on societal issues, particularly related to media and journalism

No Comments

No Known Activations