INDEX

Explanations

references to scientific and research-related measurements or values

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

words describing nouns followed by prepositions

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

下载附件

-0.42

 لينك

-0.37

 piele

-0.35

WithMany

-0.35

Біографія

-0.35

 المعيارى

-0.35

 ujednoznacz

-0.35

Begriffsklä

-0.34

 nhảy

-0.30

SECONDS

-0.29

POSITIVE LOGITS

 FetchType

0.58

xnn

0.56

findpost

0.52

addContainerGap

0.52

fromnode

0.51

AxisAlignment

0.50

 ivelany

0.50

 VIDEOTAPE

0.49

AccessorTable

0.47

 мәкал

0.47

Activations Density 0.352%

references to scientific and research-related measurements or values

words describing nouns followed by prepositions

No Comments

No Known Activations