INDEX

Explanations

expressions of gratitude

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

expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 DbSet

-0.40

`.`

-0.36

migrationBuilder

-0.35

))->

-0.35

 Cumberland

-0.34

idual

-0.34

sery

-0.33

 sexual

-0.33

éry

-0.33

])->

-0.32

POSITIVE LOGITS

Thanks

1.63

 Thanks

1.56

thanks

1.30

THANKS

1.28

 THANKS

1.25

 thanks

1.18

Gracias

1.14

 Gracias

1.13

Thx

1.07

Danke

1.05

Activations Density 0.005%

expressions of gratitude

expressions of gratitude

No Comments

No Known Activations