INDEX

Explanations

terms related to applications and industries, especially in the context of materials and products

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

Personendaten

-0.77

ValueStyle

-0.65

 المعيارى

-0.65

 esternos

-0.61

 Numerade

-0.59

 autorytatywna

-0.57

MigrationBuilder

-0.53

LOYEES

-0.53

aktery

-0.53

 للمعارف

-0.52

POSITIVE LOGITS

 applications

1.78

 uses

1.74

 Uses

1.67

用途

1.61

 application

1.56

Uses

1.55

 Applications

1.55

 usage

1.54

Applications

1.53

applications

1.51

Activations Density 0.591%

terms related to applications and industries, especially in the context of materials and products

No Comments

No Known Activations