INDEX

Explanations

occurrences of the word "new" in various contexts related to programming and data structures

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

declaring new arrays and objects

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

/**

-0.55

IAction

-0.48

Identyfik

-0.45

Amicalement

-0.44

ModelAdmin

-0.43

 opérateur

-0.42

 accès

-0.42

 ConstraintSet

-0.42

Искәрмәләр

-0.42

 ostavi

-0.41

POSITIVE LOGITS

IBOutlet

0.55

MigrationBuilder

0.48

devamını

0.48

StoryboardSegue

0.48

">//

0.46

 ModelExpression

0.44

 estekak

0.44

 AssemblyVersion

0.42

 &___

0.42

principalColumn

0.41

Activations Density 0.003%

occurrences of the word "new" in various contexts related to programming and data structures

declaring new arrays and objects

No Comments

No Known Activations