INDEX

Explanations

programming terms and syntax related to class definitions and layouts

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

code blocks and programming syntax

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

NameInMap

-0.51

 Ceinture

-0.48

出版年

-0.46

JspWriter

-0.45

adaptiveStyles

-0.42

تقاوى

-0.41

jalá

-0.41

 mxArray

-0.41

 turun

-0.40

PreInfinity

-0.40

POSITIVE LOGITS

yntaxException

0.41

 Paglinawan

0.39

клопе

0.38

xtext

0.37

tgär

0.36

 JpaRepository

0.36

verwijspagina

0.35

RenderAtEndOf

0.35

DoubleQuotes

0.35

oline

0.34

Activations Density 0.150%

programming terms and syntax related to class definitions and layouts

code blocks and programming syntax

No Comments

No Known Activations