INDEX

Explanations

elements that indicate conditional logic or thread statuses in programming environments

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

Code related to thread management

np_acts-logits-general · gemini-2.0-flash

ref-type="table" or fig

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

 préférences

-0.58

 ComVisible

-0.52

InvalidProtocol

-0.51

FAC

-0.51

 Antal

-0.50

PasswordEncoder

-0.49

 schlagen

-0.48

 assunto

-0.47

GeneratedMessage

-0.47

zielle

-0.47

POSITIVE LOGITS

WriteHeader

0.58

 وتسجيلات

0.58

therin

0.57

Kjelder

0.55

 Glamour

0.54

 Bewer

0.53

GetMapping

0.51

 valence

0.51

afficheront

0.50

MemberId

0.50

Activations Density 0.192%

elements that indicate conditional logic or thread statuses in programming environments

Code related to thread management

ref-type="table" or fig

No Comments

No Known Activations