INDEX

Explanations

phrases indicating relationships and attributes related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

setVerticalGroup

-0.89

 defaultstate

-0.76

 dentelle

-0.75

دانشنامهٔ

-0.75

OGND

-0.72

 мәкал

-0.72

 sfeer

-0.72

 betweenstory

-0.72

 vôtre

-0.72

ViewImports

-0.72

POSITIVE LOGITS

 interests

0.69

 knowledge

0.67

 aspirations

0.65

 disabilities

0.64

 ambitions

0.62

 experience

0.60

 skills

0.59

 background

0.58

 passion

0.56

 hobbies

0.56

Activations Density 0.442%

phrases indicating relationships and attributes related to individuals

No Comments

No Known Activations