INDEX

Explanations

references to time periods, specifically years and annual cycles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

IntoConstraints

-0.70

//

-0.66

ultas

-0.59

DockStyle

-0.57

ciutto

-0.54

GridData

-0.54

adze

-0.53

 esternos

-0.53

friday

-0.53

oogle

-0.52

POSITIVE LOGITS

 year

1.99

 years

1.79

year

1.74

 Year

1.67

years

1.65

 YEAR

1.65

Year

1.63

 année

1.49

YEAR

1.49

Years

1.49

Activations Density 0.276%

references to time periods, specifically years and annual cycles

No Comments

No Known Activations