INDEX

Explanations

technical terms and related commands in programming or configuration settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

medriver

-0.43

ViewImports

-0.39

UnifiedTopology

-0.38

Geo

-0.37

geo

-0.36

bewerken

-0.35

//$

-0.34

imageshack

-0.34

Selfer

-0.33

tagext

-0.33

POSITIVE LOGITS

 Chwiliwch

0.74

 kasarigan

0.71

principalColumn

0.59

 ivelany

0.58

webElementXpaths

0.57

Panamoan

0.56

RuleContext

0.53

 viewDidLoad

0.48

ніципа

0.48

Hozzáférés

0.48

Activations Density 1.599%

technical terms and related commands in programming or configuration settings

No Comments

No Known Activations