INDEX

Explanations

expressions of gratitude

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

"thanks" or related phrases

np_acts-logits-general · gemini-2.0-flash

thanks to

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 sitten

-0.32

犯

-0.31

fly

-0.31

 podstaw

-0.30

 Blatt

-0.29

abs

-0.29

ambilan

-0.28

 would

-0.28

 attempt

-0.27

vyk

-0.27

POSITIVE LOGITS

 thanks

1.39

 graças

1.32

thanks

1.30

Благодаря

1.28

 благодаря

1.28

 grâce

1.23

 gracias

1.20

 THANKS

1.20

 dzięki

1.20

 Thanks

1.20

Activations Density 0.157%

expressions of gratitude

"thanks" or related phrases

thanks to

No Comments

No Known Activations