INDEX

Explanations

references to the English language and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

Personensuche

-0.47

featureID

-0.45

parsedMessage

-0.44

__(/*!

-0.44

 hikariConfig

-0.43

ViewImports

-0.43

tinyos

-0.40

Hentet

-0.39

 Normdatei

-0.39

POSITIVE LOGITS

speaking

1.03

 speaking

0.98

 language

0.95

 Speaking

0.85

language

0.81

 Language

0.81

Speaking

0.80

 LANGUAGE

0.72

Language

0.69

anguage

0.68

Activations Density 0.246%

references to the English language and its variations

No Comments

No Known Activations