INDEX

Explanations

expressions of gratitude and appreciation

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

"Thank you" or gratitude

np_acts-logits-general · gemini-2.0-flash

thank you very much

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 ſche

-0.62

 Мексичка

-0.60

 Houſe

-0.58

 purpoſe

-0.57

Fandom

-0.56

 Diſ

-0.56

<_>

-0.56

깥

-0.56

 houſe

-0.55

]=>

-0.54

POSITIVE LOGITS

 very

1.55

very

1.15

 VERY

1.07

Very

1.04

 Very

1.01

 sehr

1.00

 très

0.98

 muito

0.96

 bardzo

0.95

 sincerely

0.91

Activations Density 0.048%

expressions of gratitude and appreciation

"Thank you" or gratitude

thank you very much

No Comments

No Known Activations