INDEX

Explanations

phrases related to decision-making and commitment within relationships

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

readiness to change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.47

NameInMap

-0.43

épend

-0.42

ifikationer

-0.39

Géographie

-0.39

Datuak

-0.37

 getRule

-0.37

 Wiktionnaire

-0.36

grano

-0.35

esez

-0.35

POSITIVE LOGITS

 COMMIT

0.55

willing

0.53

 commitment

0.52

Commitment

0.50

 willingness

0.50

 desire

0.48

OGND

0.48

commitment

0.47

 commit

0.47

 committed

0.47

Activations Density 0.077%

phrases related to decision-making and commitment within relationships

readiness to change

No Comments

No Known Activations