INDEX

Explanations

dates and settings-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

GEBURTSDATUM

-1.15

 Exactos

-0.88

Efq

-0.88

 transfieras

-0.85

 kaarangay

-0.82

MigrationBuilder

-0.82

contentLoaded

-0.82

BeginContext

-0.80

richTextPanel

-0.79

 Diretto

-0.78

POSITIVE LOGITS

Settings

0.88

д

0.70

자

0.68

Usuario

0.68

 Mont

0.53

Floating

0.53

 Matheson

0.52

usuario

0.52

стори

0.51

 Bion

0.51

Activations Density 0.535%

dates and settings-related terms

No Comments

No Known Activations