INDEX

Explanations

class definitions and their methods in programming code

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

Code related to class definitions and method calls

np_acts-logits-general · gemini-2.0-flash

printing output

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 correspondance

-0.59

icksburg

-0.57

 covenants

-0.53

 Biôgrafia

-0.51

曖昧さ回避

-0.50

 setempat

-0.50

 waveforms

-0.48

أما

-0.48

 camps

-0.47

 Allí

-0.47

POSITIVE LOGITS

 toString

0.71

Println

0.66

 print

0.60

 Person

0.58

Console

0.58

PrintStream

0.55

 Print

0.54

 printed

0.54

ArgsConstructor

0.54

age

0.54

Activations Density 0.141%

class definitions and their methods in programming code

Code related to class definitions and method calls

printing output

No Comments

No Known Activations