INDEX

Explanations

names and references of authors or contributors in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

ônicos

-0.77

êmio

-0.70

polazione

-0.66

 Filho

-0.65

 Antônio

-0.65

 متعلقه

-0.64

LookAnd

-0.63

 confiable

-0.63

ômico

-0.63

 Mejía

-0.62

POSITIVE LOGITS

ⓧ

1.08

momix

0.66

KommentareTeilen

0.66

 authorised

0.65

MADRID

0.65

ginate

0.64

authorised

0.64

cognised

0.63

idorm

0.63

(£

0.63

Activations Density 0.214%

names and references of authors or contributors in a document

No Comments

No Known Activations