INDEX

Explanations

default keyword usage in programming contexts

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

else, otherwise, default

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 queſta

-0.73

 transfieras

-0.69

Diweddarwch

-0.65

$_(

-0.65

⟬

-0.65

OGND

-0.64

 Biôgrafia

-0.60

 ComVisible

-0.60

rungsseite

-0.59

ScopeManager

-0.58

POSITIVE LOGITS

0.47

/*

0.36

 Kasus

0.36

/*

0.35

Nothing

0.35

default

0.35

 Nothing

0.34

EDEFAULT

0.33

 edición

0.32

eterangan

0.32

Activations Density 0.003%

default keyword usage in programming contexts

else, otherwise, default

No Comments

No Known Activations