INDEX

Explanations

numerical values associated with measurements and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

rungsseite

-0.73

ſelf

-0.60

 متعلقه

-0.57

 próprio

-0.56

LookAnd

-0.56

.*")]

-0.55

 yourselves

-0.53

__*/

-0.53

 próprios

-0.53

 iſt

-0.52

POSITIVE LOGITS

 Réponses

0.74

principalColumn

0.64

US

0.60

 محفوظة

0.57

ⓧ

0.56

ochial

0.56

imageshack

0.54

jooq

0.52

nvarchar

0.51

 noqa

0.51

Activations Density 0.510%

numerical values associated with measurements and dimensions

No Comments

No Known Activations