INDEX

Explanations

references to programming concepts related to user interface transitions and data management in code

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

segue identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

存于互联网档案馆

-0.59

 EconPapers

-0.59

ंदीखरीदारी

-0.49

 Taktlose

-0.46

 Normdatei

-0.46

 nakalista

-0.46

 مواليد

-0.45

 समीक्षाएं

-0.44

GraphicsUnit

-0.43

 становника

-0.43

POSITIVE LOGITS

StoryboardSegue

0.73

Segue

0.66

withIdentifier

0.52

 segue

0.49

segue

0.47

WithIdentifier

0.45

AISSEE

0.43

verwijspagina

0.42

 Selig

0.40

Seg

0.38

Activations Density 0.001%

references to programming concepts related to user interface transitions and data management in code

segue identifiers

No Comments

No Known Activations