INDEX

Explanations

references to data formats, versions, or structural components in a technical context

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 ability

-0.52

she

-0.50

ism

-0.46

ern

-0.46

 StatelessWidget

-0.43

())));

-0.43

Здравствуйте

-0.42

bigint

-0.42

she

-0.42

kript

-0.42

POSITIVE LOGITS

TargetException

0.74

DeleteBehavior

0.73

AnchorStyles

0.73

GeneratedCode

0.71

 StringTokenizer

0.68

Tazama

0.67

 kasarigan

0.66

 Allociné

0.66

पया

0.64

énario

0.64

Activations Density 0.397%

references to data formats, versions, or structural components in a technical context

No Comments

No Known Activations