INDEX

Explanations

references to items or segments categorized as "pieces" 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

,:);

-0.84

expandindo

-0.76

)"),

-0.75

ValueStyle

-0.74

 StatefulWidget

-0.73

 useStyles

-0.72

,:,

-0.70

>`;

-0.70

oneofs

-0.69

])):

-0.68

POSITIVE LOGITS

 piece

0.76

piece

0.76

Piece

0.64

 Penh

0.59

cault

0.57

 Piece

0.57

 peace

0.54

 makes

0.52

pieces

0.50

urp

0.49

Activations Density 0.157%

references to items or segments categorized as "pieces" in various contexts

No Comments

No Known Activations