INDEX

Explanations

phrases indicating medical conditions, their complications, or underlying factors impacting health

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

inherent/implicit/underlying conditions

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

 BorderRadius

-0.48

 waer

-0.46

nonatomic

-0.43

yelitis

-0.41

ImageContext

-0.41

 Lizard

-0.40

身長

-0.39

 heirs

-0.38

 Scalars

-0.38

aruhi

-0.37

POSITIVE LOGITS

centralwidget

0.49

complexContent

0.45

BufferException

0.45

]))

0.44

@"/

0.43

")));

0.43

󠁣

0.43

󠁴

0.42

Життєпис

0.42

?».

0.42

Activations Density 0.139%

phrases indicating medical conditions, their complications, or underlying factors impacting health

inherent/implicit/underlying conditions

No Comments

No Known Activations