INDEX

Explanations

references to family, housing needs, and socioeconomic status

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

families and individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 manhood

-0.41

 analog

-0.39

 Glanz

-0.36

 susp

-0.35

Tē

-0.35

 trait

-0.34

EMBER

-0.33

 gratuitos

-0.33

LLocation

-0.33

 hall

-0.32

POSITIVE LOGITS

 families

0.71

Families

0.70

 Familie

0.68

 Familien

0.68

 Families

0.66

 family

0.66

 buyers

0.65

 famiglie

0.65

 parejas

0.64

families

0.64

Activations Density 0.013%

references to family, housing needs, and socioeconomic status

families and individuals

No Comments

No Known Activations