INDEX

Explanations

mentions of the color blue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

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

 Roskov

-0.75

 Wikimedijinoj

-0.68

WebVitals

-0.62

RenderAtEndOf

-0.61



-0.60

 autorytatywna

-0.59

లాలు

-0.57

HasAnnotation

-0.57

 Италијани

-0.57

Хьажоргаш

-0.57

POSITIVE LOGITS

URLException

0.62

canestro

0.49

Turning

0.45

 Turning

0.45

 Blue

0.44

azul

0.43

 Theore

0.41

 Lordships

0.41

spesies

0.40

fromnode

0.40

Activations Density 0.255%

mentions of the color blue

No Comments

No Known Activations