INDEX

Explanations

expressions related to growth and development over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

 growth

-0.85

 Growth

-0.75

growth

-0.74

Growth

-0.72

 GROWTH

-0.65

 growing

-0.61

 crecimiento

-0.58

Growing

-0.57

 Growing

-0.57

GROW

-0.54

POSITIVE LOGITS

 pains

0.79

 taller

0.68

 stronger

0.65

 accustomed

0.61

 spurt

0.60

 fonder

0.58

 exponentially

0.57

 beards

0.57

 leaps

0.56

 wings

0.56

Activations Density 0.140%

expressions related to growth and development over time

No Comments

No Known Activations