INDEX

Explanations

phrases related to data structures and their attributes in programming

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

mathematical or code context separators

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

TintMode

-0.57

expandindo

-0.56

InjectAttribute

-0.56

extAlignment

-0.55

 ویکی‌پدی

-0.55

MathML

-0.50

yntaxException

-0.48

 Italijanski

-0.48

 surla

-0.47

ngdoc

-0.45

POSITIVE LOGITS

 Dorsey

0.38

"]();

0.34

(_.

0.33

 contributes

0.31

Tracce

0.31

 nodes

0.31

진

0.30

ged

0.30

 symbols

0.30

隈

0.30

Activations Density 0.017%

phrases related to data structures and their attributes in programming

mathematical or code context separators

No Comments

No Known Activations