INDEX

Explanations

references to rows and the concept of counting within a dataset

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

"Row" or "row"

np_acts-logits-general · gemini-2.0-flash

data structure geometry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 متعلقه

-0.70

MENAFN

-0.68

 Réponses

-0.65

QMetaType

-0.65

 especiais

-0.64

 élevées

-0.64

")));

-0.63

رير

-0.63

 sanitarios

-0.63

?>">

-0.62

POSITIVE LOGITS

TypedDataSet

0.86

 numberOfRows

0.84

Row

0.80

 rows

0.79

 Rowland

0.75

row

0.74

ROW

0.74

rowData

0.65

keyColumn

0.65

 Rows

0.64

Activations Density 0.050%

references to rows and the concept of counting within a dataset

"Row" or "row"

data structure geometry

No Comments

No Known Activations