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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

protoimpl

-0.52

 Always

-0.50

nostic

-0.50

 EClass

-0.49

etc

-0.48

-0.46

 Both

-0.46

 dagegen

-0.46

 Otherwise

-0.46

ضي

-0.45

POSITIVE LOGITS

 thanks

2.21

 courtesy

1.52

 gracias

1.49

 graças

1.48

thanks

1.39

 grazie

1.33

courtesy

1.31

 grâce

1.21

 THANKS

1.18

 owing

1.14

Activations Density 0.143%

expressions of gratitude

No Comments

No Known Activations