INDEX

Explanations

keywords related to assistance and improvement in services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

AnchorStyles

-0.72

 nahilalakip

-0.66

ViewFeatures

-0.57

allowNull

-0.56

 inſ

-0.54

 numberOfRows

-0.54

holde

-0.52

 Inſ

-0.52

 Conſ

-0.51

ูป

-0.51

POSITIVE LOGITS

 Италијани

0.73

 שוליים

0.71

Autoritní

0.62

TypedDataSet

0.60

__':

0.60

__':

0.59

InjectAttribute

0.59

titleMargin

0.59

RegressionTest

0.59

Vidite

0.59

Activations Density 0.296%

keywords related to assistance and improvement in services

No Comments

No Known Activations