INDEX

Explanations

expressions of gratitude and appreciation

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

Appreciation, followed by a positive statement

np_acts-logits-general · gemini-2.0-flash

thank you

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ARROLL

-0.45

 Democrá

-0.43

rücke

-0.42

cala

-0.40

etwork

-0.40

envie

-0.40

 drift

-0.40

 speciali

-0.40

LineChart

-0.40

CompleteListener

-0.40

POSITIVE LOGITS

 thank

1.64

 Thank

1.46

 thanks

1.45

 THANK

1.43

Thank

1.37

 THANKS

1.36

thank

1.35

 Thanks

1.34

thanks

1.33

THANK

1.30

Activations Density 0.132%

expressions of gratitude and appreciation

Appreciation, followed by a positive statement

thank you

No Comments

No Known Activations