INDEX

Explanations

specific numerical values or references related to distance or measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

出版年

-0.68

DataItem

-0.54

aquí

-0.52

lì

-0.52

Nouvelle

-0.52

 maisha

-0.52

DotNetBar

-0.50

время

-0.50

ča

-0.49

 gradova

-0.49

POSITIVE LOGITS

 autorytatywna

1.02

GEBURTSDATUM

0.85

IContainer

0.79

MigrationBuilder

0.75

migrationBuilder

0.75

Hauptartikel

0.75

 AssemblyProduct

0.73

])):

0.65

reonine

0.63

NUMX

0.63

Activations Density 0.000%

specific numerical values or references related to distance or measurement

No Comments

No Known Activations