INDEX

Explanations

references to chores and related activities

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

chores and choreography

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 informée

-0.61

EnableWeb

-0.54

 reserva

-0.51

 Embaj

-0.50

 Portuguesa

-0.48

 Frankel

-0.48

openssl

-0.48

 Maximilian

-0.48

 Popov

-0.48

 salvaje

-0.47

POSITIVE LOGITS

 chore

1.78

 chores

1.63

 Chore

1.44

Chore

1.34

 chor

0.84

Chor

0.71

 choreography

0.70

 Chor

0.68

chor

0.66

 tasks

0.66

Activations Density 0.003%

references to chores and related activities

chores and choreography

No Comments

No Known Activations