INDEX

Explanations

references to Irish culture, individuals, or elements associated with Ireland

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

RegressionTest

-1.00

 propOrder

-0.79

 Andersson

-0.72

iertos

-0.66

Datuak

-0.66

 springfox

-0.64

 Púb

-0.64

vym

-0.64

TintMode

-0.64

 correctes

-0.63

POSITIVE LOGITS

 Irish

1.41

 Ireland

1.31

Irish

1.29

Ireland

1.24

 IRELAND

1.20

 irland

1.17

 Irishman

1.16

 Irland

1.08

 Irlanda

1.06

 irish

1.04

Activations Density 0.334%

references to Irish culture, individuals, or elements associated with Ireland

No Comments

No Known Activations