INDEX

Explanations

programming constructs and classes used for data manipulation and graphical user interface design

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

<bos>

-0.69

 daarvan

-0.57

ſelf

-0.55

 Etrus

-0.54

"}")

-0.53

//});

-0.51

 Evita

-0.50

[]

-0.50

>)</

-0.49

脚注の使い方

-0.49

POSITIVE LOGITS

ReusableCell

0.85

SharedCtor

0.83

ModelAdmin

0.76

TestingModule

0.75

WriteTagHelper

0.72

openConnection

0.71

 IndexPath

0.71

 InputDecoration

0.70

ImageContext

0.69

 createSlice

0.69

Activations Density 0.173%

programming constructs and classes used for data manipulation and graphical user interface design

No Comments

No Known Activations