INDEX

Explanations

references to menus and menu items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

expandindo

-0.83

-0.74

]))

-0.74

()))

-0.72

%</

-0.72

('.');

-0.72

'));

-0.70

WriteBarrier

-0.69

 \%$\\

-0.69

cepción

-0.69

POSITIVE LOGITS

 menu

1.85

 Menu

1.84

 menus

1.75

 MENU

1.54

Menu

1.53

menu

1.48

 Menus

1.44

MENU

1.41

getMenu

1.34

Menus

1.27

Activations Density 0.107%

references to menus and menu items

No Comments

No Known Activations