INDEX

Explanations

code and programming-related terms, particularly in the context of application structure and setup

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

 собой

-0.49

sprechen

-0.47

وانه

-0.45

 semula

-0.44

 tege

-0.44

 собою

-0.42

cinogenicity

-0.40

 Hollow

-0.40

 transgression

-0.40

 roule

-0.39

POSITIVE LOGITS

IContainer

0.94

expandindo

0.76

setupUi

0.71

rungsseite

0.71

contentLoaded

0.68

 Wiktionnaire

0.67

LookAnd

0.66

StoryboardSegue

0.66

 TestBed

0.65

 otomatig

0.65

Activations Density 0.047%

code and programming-related terms, particularly in the context of application structure and setup

No Comments

No Known Activations