INDEX

Explanations

references to authoritative content or structural elements of writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoreMessageInfo

-0.63

 MessageBoxIcon

-0.54

 voir

-0.53

motiv

-0.53

__":

-0.52

makeText

-0.50

apimachinery

-0.46

új

-0.45

Népesség

-0.45

Наводи

-0.43

POSITIVE LOGITS

Personendaten

0.90

ⓧ

0.76

出版年

0.74

MessageTagHelper

0.68

KommentareTeilen

0.65

__(/*!

0.64

LabelTagHelper

0.59

Tikang

0.55

Obrázky

0.54

verifyException

0.53

Activations Density 0.511%

references to authoritative content or structural elements of writing

No Comments

No Known Activations