INDEX

Explanations

phrases indicating a call to action or a sense of duty

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

 intrigu

-0.57

 endeav

-0.52

 endeavouring

-0.52

 apprehen

-0.51

🕗

-0.50

 Varan

-0.49

 AMAZ

-0.49

 impelled

-0.49

 vainly

-0.48

 ineffec

-0.48

POSITIVE LOGITS

igneur

0.63

 prostitu

0.63

 pulsante

0.61

 utop

0.58

 notor

0.58

 hunde

0.57

 pantal

0.57

 ideolog

0.56

 matel

0.56

 meras

0.55

Activations Density 0.105%

phrases indicating a call to action or a sense of duty

No Comments

No Known Activations