INDEX

Explanations

references to brands and branding

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

 Parigi

-0.91

Дереккөздер

-0.88

/*

-0.86

 Deputies

-0.83

 Cytometry

-0.83

 Watcher

-0.83

 alimony

-0.78

فيه

-0.78

 Avila

-0.77

 Мексичка

-0.77

POSITIVE LOGITS

 brands

1.45

 BRAND

1.45

 brand

1.38

brands

1.37

Brands

1.34

BRAND

1.33

 Brand

1.32

brand

1.28

 Brands

1.25

 Brandt

1.24

Activations Density 0.026%

references to brands and branding

No Comments

No Known Activations