INDEX

Explanations

code constructs related to data binding and view models in software development

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

<start_of_turn> user

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

 AssemblyCulture

-0.54

">//

-0.51

 autorytatywna

-0.51

קישורים

-0.50

Tikang

-0.47

DockStyle

-0.45

 defaultstate

-0.45

GOTREF

-0.44

KEYCODE

-0.44

iastes

-0.43

POSITIVE LOGITS

存于互联网档案馆

0.44

 ModelExpression

0.39

énario

0.38

Tembelea

0.38

份

0.37

 practise

0.36

 LUMP

0.34

 Requ

0.34

posals

0.34

 nakalista

0.34

Activations Density 0.005%

code constructs related to data binding and view models in software development

<start_of_turn> user

No Comments

No Known Activations