INDEX

Explanations

numerical expressions related to time or duration

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

Numbers followed by time units

np_acts-logits-general · gemini-2.0-flash

number of years months days

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

RectangleBorder

-0.70

 ModelExpression

-0.69

исленность

-0.63

ContentAsync

-0.62

providedIn

-0.62

 Bewußt

-0.60

 للاسماء

-0.59

 חיצוניים

-0.58

 kän

-0.57

 kasarigan

-0.56

POSITIVE LOGITS

 months

0.70

 weeks

0.60

 days

0.56

 years

0.55

 consecutive

0.52

 month

0.49

 MONTHS

0.47

months

0.46

 Months

0.44

Months

0.44

Activations Density 0.204%

numerical expressions related to time or duration

Numbers followed by time units

number of years months days

No Comments

No Known Activations