INDEX

Explanations

references to titles and proper nouns

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

 Partagez

-0.80

 disambiguazione

-0.79

ChromeDriver

-0.72

ItemBackground

-0.71

Vidite

-0.71

 hObject

-0.69

 ivelany

-0.69

WireFormat

-0.69

 avoit

-0.68

 auroit

-0.68

POSITIVE LOGITS

THE

0.88

The

0.76

THE

0.73

The

0.73

🏻

0.67

0.59

Portale

0.58

ETHING

0.57

Di

0.56

География

0.56

Activations Density 0.221%

references to titles and proper nouns

No Comments

No Known Activations