INDEX

Explanations

references to Indigenous peoples and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Colette

-0.92

Życiorys

-0.91

 useState

-0.87

gdx

-0.85

NSM

-0.81

IsContent

-0.81

 Enugu

-0.79

geries

-0.79

 Zuckerberg

-0.79

verwijspagina

-0.78

POSITIVE LOGITS

 Indian

1.20

INDIAN

1.12

 Indians

1.11

Indian

1.09

 INDIAN

1.08

 indian

1.05

indian

1.02

Indians

1.00

 indios

0.78

 Anderson

0.66

Activations Density 0.009%

references to Indigenous peoples and related terms

No Comments

No Known Activations