INDEX

Explanations

terms related to "co-" prefixes, indicating collaboration or cooperative relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.83

 paramString

-0.80

 useParams

-0.73

mush

-0.69

 Picchu

-0.69

 Thiết

-0.68

 Pust

-0.68

anthene

-0.67

lernen

-0.64

Portail

-0.64

POSITIVE LOGITS

Co

1.48

Co

1.43

 Colette

1.32

co

1.31

Coz

1.27

Cob

1.22

 covariates

1.20

 Coen

1.19

CoA

1.18

co

1.16

Activations Density 0.215%

terms related to "co-" prefixes, indicating collaboration or cooperative relationships

No Comments

No Known Activations