INDEX

Explanations

Java code constructs related to JSON deserialization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 itſelf

-0.82

LookAnd

-0.80

 فريبيس

-0.80

featureID

-0.78

 ویکی‌پدیا

-0.77

 AssemblyCulture

-0.76

 Theſe

-0.76

 Мексичка

-0.74

TestingModule

-0.74

expandindo

-0.71

POSITIVE LOGITS

]}>

0.49

허

0.48

<eos>

0.43

 Shetterly

0.43

hance

0.42

 }^{*}

0.42

 mema

0.41

((

0.41

 Schumacher

0.41

olella

0.41

Activations Density 0.340%

Java code constructs related to JSON deserialization

No Comments

No Known Activations