INDEX

Explanations

code-related constructs and terms in a programming context, particularly related to threads and locking mechanisms

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

Brackets enclosing letters or symbols

np_acts-logits-general · gemini-2.0-flash

indices, `i`, `j`, `k`, `r`

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

}?>

-0.66

}{*}{}

-0.55

">=

-0.54

RenderAtEndOf

-0.54

UserScript

-0.53

}}}$

-0.53

ตร

-0.52

}?>

-0.52

"}")

-0.51

>}

-0.50

POSITIVE LOGITS

 CreateTagHelper

0.95

 MainAxisSize

0.81

fromnode

0.68

ReusableCell

0.60

msgSender

0.60

 kiezen

0.58

 opérés

0.56

дожник

0.56

 Référence

0.55

 skimage

0.54

Activations Density 0.654%

code-related constructs and terms in a programming context, particularly related to threads and locking mechanisms

Brackets enclosing letters or symbols

indices, `i`, `j`, `k`, `r`

No Comments

No Known Activations