INDEX

Explanations

words and phrases related to pairing or complementing items

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

phrases suggesting a good pairing or combination of things.

oai_token-act-pair · gemini-1.5-pro Triggered by @nrbln

words and phrases indicating complementary or well-matched items or concepts.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @nrbln

relating to "complement" or "compliment"

np_acts-logits-general · gemini-2.0-flash

go together

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Trichloroethane

-0.43

 Eder

-0.36

 yatak

-0.35

 autorité

-0.35

 عل

-0.35

 mecánica

-0.34

hahah

-0.34

 Primaria

-0.34

 astore

-0.34

haha

-0.34

POSITIVE LOGITS

 complement

0.73

 complements

0.71

complement

0.68

 abbin

0.67

 compliment

0.67

Complement

0.66

 Complement

0.65

 Pairing

0.64

 pairing

0.63

 partner

0.62

Activations Density 0.322%

words and phrases related to pairing or complementing items

phrases suggesting a good pairing or combination of things.

words and phrases indicating complementary or well-matched items or concepts.

relating to "complement" or "compliment"

go together

No Comments

No Known Activations