INDEX

Explanations

expressions of gratitude and appreciation

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

Appreciation, thanks, and acknowledgements

np_acts-logits-general · gemini-2.0-flash

thank you, thanks, appreciate

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aarrggbb

-0.66

wpi

-0.53

fromnode

-0.52

elif

-0.50

ngths

-0.50

 behaup

-0.49

AntiForgeryToken

-0.49

 thous

-0.48

 jutaan

-0.48

?”

-0.47

POSITIVE LOGITS

 effectivement

0.85

 inderdaad

0.82

 unfortunately

0.77

 fakty

0.73

ImageContext

0.69

 Appreciate

0.69

+#+#

0.68

KommentareTeilen

0.67

 appreciate

0.67

 indeed

0.67

Activations Density 0.133%

expressions of gratitude and appreciation

Appreciation, thanks, and acknowledgements

thank you, thanks, appreciate

No Comments

No Known Activations