INDEX

Explanations

references to landscapes and their 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

@"/

-0.94

antMatchers

-0.73

 amitié

-0.73

ഞ

-0.72

 superstitious

-0.71

 laiton

-0.70

 chers

-0.70

 tué

-0.69

 médicale

-0.67

 nicio

-0.67

POSITIVE LOGITS

 landscape

2.15

 landscapes

1.92

 Landscape

1.83

landscape

1.78

Landscape

1.77

 LANDSCAPE

1.63

 Landscapes

1.50

 paysage

1.36

SCAPE

1.34

 paisaje

1.24

Activations Density 0.056%

references to landscapes and their design

No Comments

No Known Activations