INDEX

Explanations

phrases indicating desires and intentions

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

"Want to" followed by an action

np_acts-logits-general · gemini-2.0-flash

want to

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

MessageOf

-0.77

 تضيفلها

-0.74

 NUKAT

-0.57

bootstrapcdn

-0.56

__()

-0.54

jsonwebtoken

-0.54

LayoutStyle

-0.54

RefNanny

-0.54

NSIndexPath

-0.53

principalTable

-0.53

POSITIVE LOGITS

)");

0.61

irited

0.55

 truly

0.55

PreExecute

0.53

λία

0.52

 fine

0.52

")));

0.51

cstdlib

0.50

endphp

0.50

endpush

0.49

Activations Density 0.108%

phrases indicating desires and intentions

"Want to" followed by an action

want to

No Comments

No Known Activations