INDEX

Explanations

references to windows 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 @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

-0.79

 élect

-0.76

agissait

-0.75

 Zeke

-0.74

 découver

-0.73

 variés

-0.71

 passés

-0.71

 loisirs

-0.71

✨:

-0.70

 espirituales

-0.70

POSITIVE LOGITS

 windows

1.49

 window

1.49

 Window

1.40

 Windows

1.29

window

1.28

Windows

1.27

windows

1.27

 WINDOW

1.25

Window

1.17

WINDOW

1.16

Activations Density 0.058%

references to windows in various contexts

No Comments

No Known Activations