INDEX

Explanations

quantitative expressions indicating large amounts or comparisons

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

"More than" followed by a number

np_acts-logits-general · gemini-2.0-flash

more than 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

 SafeMath

-0.97

ItemBackground

-0.80

EDEFAULT

-0.77

 deſt

-0.69

OrBuilder

-0.69

astéroïdes

-0.68

UnitTesting

-0.67

Tembelea

-0.67

★★★★☆

-0.66

Sucesor

-0.66

POSITIVE LOGITS

 hundreds

0.63

0.60

 dozen

0.59

 dozens

0.58

 thousands

0.53

hundreds

0.49

 approximately

0.48

more

0.47

 more

0.47

 hundred

0.44

Activations Density 0.151%

quantitative expressions indicating large amounts or comparisons

"More than" followed by a number

more than quantities

No Comments

No Known Activations