INDEX

Explanations

code syntax related to Java programming, especially for generic types and method definitions

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

Java data types

np_acts-logits-general · gemini-2.0-flash

programmer's data types

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

 للاسماء

-0.96

 kasarigan

-0.77

sizeCache

-0.74

GEBURTSDATUM

-0.70

Décès

-0.66

StoreMessageInfo

-0.65

لينكات

-0.60

 تضيفلها

-0.57

 שוליים

-0.56

AndEndTag

-0.56

POSITIVE LOGITS

 Integer

1.73

Integer

1.65

 Boolean

1.17

Boolean

1.07

 Long

1.03

Double

1.02

 Double

0.98

Float

0.98

Long

0.91

 Float

0.88

Activations Density 0.085%

code syntax related to Java programming, especially for generic types and method definitions

Java data types

programmer's data types

No Comments

No Known Activations