INDEX

Explanations

code structure elements and programming language keywords

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

Followed by "public" in code

np_acts-logits-general · gemini-2.0-flash

public declarations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

cche

-0.57

 rend

-0.49

lero

-0.48

zyński

-0.48

miec

-0.47

lho

-0.47

IZING

-0.47

λλα

-0.46

ankin

-0.45

Mit

-0.45

POSITIVE LOGITS

 للمعارف

0.70

 ModelExpression

0.66

MLLoader

0.66

protected

0.64

static

0.63

__*/

0.63

出版年

0.63

 Chwiliwch

0.62

GEBURTSDATUM

0.60

EndGlobalSection

0.60

Activations Density 0.059%

code structure elements and programming language keywords

Followed by "public" in code

public declarations in code

No Comments

No Known Activations