INDEX

Explanations

the word "often" and its variations indicating frequency

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

Preceding "often"

np_acts-logits-general · gemini-2.0-flash

often

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

Спољашње

-0.68

Karla

-0.68

 Peshawar

-0.66

😽

-0.65

mazoo

-0.64

 McCarty

-0.63

GRAPHICAL

-0.62

 Transylvania

-0.61

 useDispatch

-0.59

 webdriver

-0.59

POSITIVE LOGITS

клопе

0.88

 '\\;'

0.79

 many

0.76

 MANY

0.76

 times

0.75

دانشنامهٔ

0.73

 trajets

0.72

GraphicsUnit

0.72

MANY

0.70

ation

0.70

Activations Density 0.059%

the word "often" and its variations indicating frequency

Preceding "often"

often

No Comments

No Known Activations