INDEX

Explanations

references to "Space" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

•birdbirdbirdbirdbirdbird

No Comments

Negative Logits

CloseOperation

-0.95

 ainfi

-0.85

 BorderRadius

-0.85

 themſelves

-0.82

 BitmapFactory

-0.82

 démocratie

-0.80

 étoient

-0.80

 colorés

-0.78

contentLoaded

-0.78

 avoient

-0.78

POSITIVE LOGITS

 Space

4.07

 space

4.07

Space

3.98

space

3.91

 SPACE

3.52

SPACE

3.35

 spaces

2.95

spaces

2.75

 Spaces

2.72

Spaces

2.67

Activations Density 0.061%

references to "Space" and its variations in context

No Comments

No Known Activations