INDEX

Explanations

specific values and types in a programming context, particularly regarding object attributes and function definitions

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

Code containing "0.0f"

np_acts-logits-general · gemini-2.0-flash

float literals and floating point numbers

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

mybatisplus

-0.94

 مشين

-0.94

setVerticalGroup

-0.80

Efq

-0.78

SourceChecksum

-0.77

contentLoaded

-0.76

دانشنامهٔ

-0.75

Datuak

-0.74

DockStyle

-0.73

>");

-0.70

POSITIVE LOGITS

vece

0.46

0.42

担当

0.39

 NSObject

0.39

 double

0.39

が取

0.38

TestBase

0.38

を取

0.38

ieuse

0.37

COE

0.37

Activations Density 0.183%

specific values and types in a programming context, particularly regarding object attributes and function definitions

Code containing "0.0f"

float literals and floating point numbers

No Comments

No Known Activations