INDEX

Explanations

relationships between socioeconomic status and issues affecting communities

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

benefit or loss

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

 Synod

-0.40

 TextFormField

-0.36

 Dispatcher

-0.35

愉快

-0.35

yych

-0.34

 Enum

-0.34

Enum

-0.34

征

-0.33

 venu

-0.33

/*

-0.33

POSITIVE LOGITS

 benefited

0.85

 losers

0.85

 benefiting

0.83

 benefit

0.80

benef

0.80

 Infórmanos

0.79

benefit

0.78

 benefitted

0.77

 beneficiaries

0.76

 beneficiary

0.75

Activations Density 0.043%

relationships between socioeconomic status and issues affecting communities

benefit or loss

No Comments

No Known Activations