INDEX

Explanations

instances of events tied to specific dates or occurrences

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

Numbers after "on"

np_acts-logits-general · gemini-2.0-flash

"on" followed by dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

webElementXpaths

-0.95

Personensuche

-0.88

AsUp

-0.82

 autorytatywna

-0.82

StoreMessageInfo

-0.70

 كومونز

-0.70

 فريبيس

-0.67

تقاوى

-0.66

findpost

-0.66

 ujednoznacz

-0.65

POSITIVE LOGITS

 ngày

0.67

 Tuesday

0.65

 Wednesday

0.62

 eighteenth

0.59

 Thursday

0.58

 nineteenth

0.58

 Monday

0.58

 FormControl

0.58

 twentieth

0.57

Tuesday

0.57

Activations Density 0.122%

instances of events tied to specific dates or occurrences

Numbers after "on"

"on" followed by dates

No Comments

No Known Activations