INDEX

Explanations

references to Java programming constructs and classes

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

 Virtue

-0.65

 estekak

-0.59

Revenir

-0.56

 szív

-0.55

 outfitters

-0.54

ır

-0.51

Viited

-0.50

 forefathers

-0.50

AppRoutingModule

-0.50

Edm

-0.49

POSITIVE LOGITS

 whiteColor

0.64

+#+

0.63

 AssemblyCulture

0.63

 שוליים

0.61

tanleria

0.60

 мәкал

0.59

HtmlAttribute

0.59

ViewFeatures

0.58

 transfieras

0.58

}{*}{}

0.58

Activations Density 0.029%

references to Java programming constructs and classes

No Comments

No Known Activations