INDEX

Explanations

references to "window" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 recentes

-0.80

 découver

-0.79

 grze

-0.79

 variés

-0.77

 passés

-0.75

 espirituales

-0.75

 loisirs

-0.74

 élect

-0.74

 tromper

-0.73

✨:

-0.73

POSITIVE LOGITS

 window

1.55

 windows

1.53

 Window

1.43

window

1.35

 Windows

1.31

windows

1.31

 WINDOW

1.30

Windows

1.29

Window

1.20

WINDOW

1.19

Activations Density 0.039%

references to "window" in various contexts

No Comments

No Known Activations