INDEX

Explanations

references to Android app components and their versioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ImageContext

-0.60

reportWebVitals

-0.55

topatho

-0.48

VersionUID

-0.47

 numerus

-0.45

lieg

-0.44

 SPOILERS

-0.44

geer

-0.43

impres

-0.42

くな

-0.42

POSITIVE LOGITS

widget

0.62

chakra

0.62

 MessageBoxIcon

0.60

TypedDataSet

0.60

ViewFeatures

0.60

ArgsConstructor

0.59

 AssemblyCulture

0.59

❋

0.59

 Bellow

0.58

 Judson

0.57

Activations Density 0.099%

references to Android app components and their versioning

No Comments

No Known Activations