INDEX

Explanations

phrases related to formal discussions and resolutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

Personendaten

-0.67

 CURIAM

-0.63

pexpr

-0.60

 bill

-0.59

évaluateur

-0.55

bill

-0.54

 autorytatywna

-0.53

RegressionTest

-0.51

Bill

-0.49

endphp

-0.49

POSITIVE LOGITS

 vectorielle

0.63

 graphique

0.56

XtraReports

0.55

 المعيارى

0.54

segno

0.53

énéral

0.52

 circulaire

0.52

دانشنامهٔ

0.52

ranton

0.50

eseorang

0.50

Activations Density 0.237%

phrases related to formal discussions and resolutions

No Comments

No Known Activations