INDEX

Explanations

references to specific geographic locations or entities

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

hatic

-0.50

 Munk

-0.47

 Motley

-0.45

subplot

-0.45

 Kane

-0.45

 Sudbury

-0.44

 serio

-0.44

 sérieux

-0.44

 savons

-0.44

setNum

-0.43

POSITIVE LOGITS

mybatisplus

0.77

contentLoaded

0.72

حياتها

0.70

oquia

0.68

</tfoot>

0.66

 Medellín

0.66

 Colombie

0.65

Colombia

0.65

 colomb

0.63

MessageOf

0.63

Activations Density 0.112%

references to specific geographic locations or entities

No Comments

No Known Activations

references to specific geographic locations or entities

No Comments

No Known Activations