INDEX

Explanations

different forms of the word "draw."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 OnInit

-0.65

 referenties

-0.64

onAttach

-0.63

keit

-0.59

findIndex

-0.58

 accett

-0.58

glie

-0.58

lepší

-0.56

 accepté

-0.56

 /\.(

-0.55

POSITIVE LOGITS

 drawn

1.30

 draws

1.22

 Draws

1.22

 draw

1.20

 drew

1.20

 Drawn

1.16

 Draw

1.15

 drawing

1.14

 DRAW

1.12

Draws

1.09

Activations Density 0.077%

different forms of the word "draw."

No Comments

No Known Activations