INDEX

Explanations

structured data about programming errors and vulnerabilities

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

Lines starting with a number followed by a parenthesis

np_acts-logits-general · gemini-2.0-flash

code vulnerabilities and errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

 various

-0.38

 populer

-0.37

 motivi

-0.37

Unsigned

-0.37

 Zeug

-0.37

ungkapkan

-0.36

wezi

-0.36

脲

-0.35

Ещё

-0.35

 autori

-0.35

POSITIVE LOGITS

تقاوى

0.66

:✨

0.60

 wireType

0.57

zzleHttp

0.57

SequentialGroup

0.56

EndProject

0.55

aarrggbb

0.54

webElementGuid

0.54

BagConstraints

0.52

 виправивши

0.52

Activations Density 0.652%

structured data about programming errors and vulnerabilities

Lines starting with a number followed by a parenthesis

code vulnerabilities and errors

No Comments

No Known Activations