INDEX

Explanations

Java print statements or output functions

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

"System" followed by ".out.println"

np_acts-logits-general · gemini-2.0-flash

System.out

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gebunden

-0.56

principalTable

-0.56

GEBURTSDATUM

-0.54

MessageOf

-0.53

__':

-0.51

slidesToShow

-0.50

 présidenti

-0.48

rauch

-0.48

 افتراض

-0.47

 familiar

-0.47

POSITIVE LOGITS

errHandler

0.69

System

0.67

out

0.64

 System

0.64

 odkazy

0.58

out

0.54

ArgsConstructor

0.51

 noten

0.49

zad

0.49

ContextHolder

0.49

Activations Density 0.012%

Java print statements or output functions

"System" followed by ".out.println"

System.out

No Comments

No Known Activations