INDEX

Explanations

expressions of gratitude

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

Expressing gratitude

np_acts-logits-general · gemini-2.0-flash

thanks for or to

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

◦

-0.40

SPM

-0.40

۪

-0.39

 cases

-0.37

LEA

-0.35

◦

-0.35

◗

-0.35

cipar

-0.34

CPO

-0.34

sery

-0.34

POSITIVE LOGITS

thanks

0.98

 Thanks

0.97

 thanks

0.97

 THANKS

0.93

thank

0.93

 thank

0.92

 thanking

0.89

 Thank

0.89

 remercie

0.88

Thanks

0.88

Activations Density 0.107%

expressions of gratitude

Expressing gratitude

thanks for or to

No Comments

No Known Activations