INDEX

Explanations

mentions of specific events or timings related to elections or important political occurrences

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

time or dates

np_acts-logits-general · gemini-2.0-flash

temporal indicators and quantities

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

 EconPapers

-0.49

 iprot

-0.49

 StatefulWidget

-0.49

 StatelessWidget

-0.48

quanto

-0.48

Chez

-0.47

CloseOperation

-0.47

 bParam

-0.47

erville

-0.46

 Personne

-0.46

POSITIVE LOGITS

 itself

0.67

end

0.66

 onwards

0.62

 evening

0.61

CEEDED

0.59

 FetchType

0.59

 midnight

0.58

 onAnimation

0.58

 afternoon

0.57

Unmarshaller

0.55

Activations Density 0.099%

mentions of specific events or timings related to elections or important political occurrences

time or dates

temporal indicators and quantities

No Comments

No Known Activations