INDEX

Explanations

references to geographic locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 propOrder

-0.54

 organisations

-0.45

 sponsoring

-0.42

"]();

-0.42

 مشين

-0.42

 ever

-0.41

 drives

-0.41

 keep

-0.41

inkler

-0.41

 órgãos

-0.41

POSITIVE LOGITS

OGND

0.69

 ujednoznacz

0.65

Personendaten

0.63

IsMutable

0.61

///</

0.57

 Leid

0.57

 maxn

0.55

찮

0.54

lee

0.54

 fuis

0.54

Activations Density 0.123%

references to geographic locations and addresses

No Comments

No Known Activations