INDEX

Explanations

expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 وتسجيلات

-0.70

 Egli

-0.66

omości

-0.65

іод

-0.65

 Castor

-0.64

ண்டும்

-0.64

 Majefty

-0.63

 ocurrido

-0.62

seur

-0.60

erweise

-0.59

POSITIVE LOGITS

 thank

1.03

 Thank

1.01

Thank

0.98

thank

0.94

 thanks

0.93

 THANK

0.91

kyou

0.88

Thanks

0.86

 gracias

0.85

 Thanks

0.84

Activations Density 0.035%

expressions of gratitude

No Comments

No Known Activations