INDEX

Explanations

references to programming components or classes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 صوتيه

-0.97

MigrationBuilder

-0.89

tagHelperRunner

-0.81

enderror

-0.75

 Roskov

-0.70

 Soit

-0.68

 poffe

-0.67

 protoimpl

-0.67

 TextAppearance

-0.66

RTEE

-0.65

POSITIVE LOGITS

Component

2.81

 Component

2.56

 component

1.94

component

1.83

 COMPONENT

1.62

COMPONENT

1.58

 Components

1.40

 componente

1.40

getComponent

1.31

Componentes

1.31

Activations Density 0.036%

references to programming components or classes

No Comments

No Known Activations