INDEX

Explanations

references to decision-making and potential outcomes in discussions

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

Sentences containing "could" or "might"

np_acts-logits-general · gemini-2.0-flash

possibility after certain subjects

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

contentLoaded

-0.79

InputBorder

-0.67

</caption>

-0.65

SourceChecksum

-0.61

ViewFeatures

-0.60

extAlignment

-0.59

!*\

-0.57

 OFDb

-0.56

gameserver

-0.56

:✨

-0.56

POSITIVE LOGITS

 could

2.78

could

2.41

 Could

2.29

Could

2.28

 COULD

1.86

 poderia

1.49

 könnte

1.46

 könnten

1.39

 podría

1.38

 podrían

1.33

Activations Density 0.394%

references to decision-making and potential outcomes in discussions

Sentences containing "could" or "might"

possibility after certain subjects

No Comments

No Known Activations