INDEX

Explanations

phrases related to time or duration

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

Followed by a period of time

np_acts-logits-general · gemini-2.0-flash

quantified duration of activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Bourgoin

-0.65

 intStringLen

-0.60

 ویکی‌پدیا

-0.57

mybatisplus

-0.56

InvalidProtocol

-0.55

WSER

-0.52

sidemargin

-0.52

ValueStyle

-0.51

WithIOException

-0.50

 genomen

-0.50

POSITIVE LOGITS

(&:

0.66

 identi

0.63

 nonstop

0.62

NUMX

0.60

...')

0.59

 continuous

0.59

lynol

0.58

 Lawson

0.58

calyp

0.58

Citiți

0.58

Activations Density 0.094%

phrases related to time or duration

Followed by a period of time

quantified duration of activities

No Comments

No Known Activations