INDEX

Explanations

quantitative phrases that indicate time spans or durations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 onOptions

-0.64

NetworkInfo

-0.61

richTextPanel

-0.61

 ویکی‌پدیا

-0.59

WebpackPlugin

-0.59

gonic

-0.59

resave

-0.56

strij

-0.55

 שוליים

-0.54

 fær

-0.53

POSITIVE LOGITS

 century

0.91

 decades

0.83

decade

0.70

century

0.69

 Century

0.67

 centuries

0.65

 deca

0.62

 CENTURY

0.61

 eeuw

0.60

Century

0.59

Activations Density 0.135%

quantitative phrases that indicate time spans or durations

No Comments

No Known Activations