INDEX

Explanations

the word "addition" and its structured variations or contexts used for expanding on or referencing supplementary information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 culoare

-0.48

 coupable

-0.48

 vieilles

-0.48

 păr

-0.47

cartera

-0.47

camisa

-0.46

blij

-0.46

cartão

-0.45

carteles

-0.44

couleur

-0.43

POSITIVE LOGITS

 addition

1.80

addition

1.40

 Addition

1.27

Addition

1.20

 additions

0.98

 tillegg

0.96

 additional

0.83

 Additions

0.75

 Zusätzlich

0.74

 추가

0.72

Activations Density 0.127%

the word "addition" and its structured variations or contexts used for expanding on or referencing supplementary information

No Comments

No Known Activations