INDEX

Explanations

indicators of asynchronous programming patterns

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

JSON view code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CppCodeGen

-0.57

PathVariable

-0.53

Datuak

-0.46

Filmographie

-0.45

 henvisninger

-0.45

badlogic

-0.43

 BrowserRouter

-0.41

ControllerAdvice

-0.40

ніципалі

-0.40

BindingSource

-0.40

POSITIVE LOGITS

 autorytatywna

0.63

دانشنامهٔ

0.55

WriteTagHelper

0.52

 ویکی‌پدی

0.49

 Normdatei

0.47

wä

0.46

 مشين

0.45

SequentialGroup

0.43

Jeografia

0.43

]]=

0.42

Activations Density 0.010%

indicators of asynchronous programming patterns

JSON view code

No Comments

No Known Activations