INDEX

Explanations

specific patterns related to grant numbers and identifiers in research documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 ویکی‌پدیای

-0.98

GEBURTSDATUM

-0.94

AccessorTable

-0.92

 للمعارف

-0.91

脚注の使い方

-0.88

 <=",

-0.86

-0.84

enterOuterAlt

-0.82

AddHtmlAttribute

-0.82

bootstrapcdn

-0.82

POSITIVE LOGITS

 générale

0.44

 generale

0.39

eraard

0.37

 Algarve

0.37

 mindig

0.37

 aislada

0.36

zdjęcie

0.36

 reír

0.34

 rarement

0.34

 dře

0.34

Activations Density 1.155%

specific patterns related to grant numbers and identifiers in research documents

No Comments

No Known Activations