INDEX

Explanations

numerical data and statistical values from research results

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ніципа

-0.47

 olvides

-0.46

Ngb

-0.44

GraphicsUnit

-0.41

 major

-0.39

verwijspagina

-0.39

Пусть

-0.39

 lant

-0.39

CAM

-0.39

律

-0.38

POSITIVE LOGITS

tagHelperRunner

1.06

GOTREF

1.02

 AssemblyCulture

0.86

 kasarigan

0.86

 مشين

0.85

 resourceCulture

0.81

 Réponses

0.70

 للاسماء

0.68

 وتسجيلات

0.66

AndEndTag

0.66

Activations Density 0.472%

numerical data and statistical values from research results

No Comments

No Known Activations