INDEX

Explanations

references to the word "little."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

//

-0.77

ScreenState

-0.73

 Deum

-0.70

FileChooser

-0.68

 Mahomes

-0.68

resizingMask

-0.66

Pozdrawiam

-0.66

ként

-0.66

 cheminée

-0.65

Cordialement

-0.63

POSITIVE LOGITS

 little

1.28

LITTLE

1.23

little

1.23

Little

1.20

 LITTLE

1.19

 Little

1.10

///</

1.04

bit

0.97

ittle

0.96

 Littleton

0.95

Activations Density 0.041%

references to the word "little."

No Comments

No Known Activations