INDEX

Explanations

references to individuals and their roles or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 kaarangay

-0.91

 Wikimedijinoj

-0.82

)");

-0.81

GEBURTSDATUM

-0.79

)";

-0.79

elemField

-0.78

 beginnetje

-0.77

]';

-0.76

 Référence

-0.76

 NgModule

-0.75

POSITIVE LOGITS

leştir

0.55

icksburg

0.43

portál

0.42

 همچنین

0.41

 pertanto

0.41

精力

0.41

 combinatie

0.40

Sprintf

0.39

私が

0.39

 ayrıca

0.38

Activations Density 0.159%

references to individuals and their roles or actions

No Comments

No Known Activations