INDEX

Explanations

expressions of love and affection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

Datuak

-1.12

 decembrie

-0.79

ؤلاء

-0.73

tioners

-0.72

 noiembrie

-0.69

طقة

-0.68

 Пусть

-0.68

daz

-0.67

 Scissors

-0.67

 Crossroads

-0.66

POSITIVE LOGITS

 love

1.53

 LOVE

1.45

 Love

1.36

LOVE

1.35

 loves

1.35

 Loves

1.33

loves

1.26

Love

1.25

Loves

1.24

 loving

1.23

Activations Density 0.044%

expressions of love and affection

No Comments

No Known Activations