INDEX

Explanations

references to software functionality and user guidance

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

contractions and 'out of'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 inspired

-0.35

 supporting

-0.35

and

-0.34

-0.32

WebElementEntity

-0.31

 measured

-0.30

anstalt

-0.30

ftagPool

-0.30

 geblieben

-0.29

filled

-0.29

POSITIVE LOGITS

httphttps

0.77

principalColumn

0.66

ंदीखरीदारी

0.65

 utafitiHapana

0.65

 Wiktionnaire

0.63

匿名使用者

0.62

findpost

0.60

帖最后由

0.60

 Meksiku

0.59

LookAnd

0.58

Activations Density 0.831%

references to software functionality and user guidance

contractions and 'out of'

No Comments

No Known Activations