INDEX

Explanations

structure-related terms in academic or technical writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

GEBURTSDATUM

-0.91

IUrlHelper

-0.76

Демографія

-0.74

windowFixed

-0.69

 ivelany

-0.68

expandindo

-0.65

bewerken

-0.65

 kaarangay

-0.65

contentLoaded

-0.64

Personendaten

-0.63

POSITIVE LOGITS

CppCodeGen

0.55

0.54

’

0.53

MigrationBuilder

0.52

DispatchToProps

0.50

Traceback

0.47

/***/

0.47

 CGSize

0.46

 ponerse

0.45

0.44

Activations Density 0.151%

structure-related terms in academic or technical writing

No Comments

No Known Activations