INDEX

Explanations

terms related to scoring and performance metrics in a game context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

évaluateur

-0.67

ponses

-0.67

EndInit

-0.66

NSYLVANIA

-0.56

ffindor

-0.54

 betweenstory

-0.53

owol

-0.51

 }}"></

-0.51

”—

-0.50

nestjs

-0.47

POSITIVE LOGITS

XmlAccessorType

0.77

contentLoaded

0.71

 مشين

0.69

noinspection

0.63

 insuffisamment

0.59

expandindo

0.58

PONENTS

0.55

ⓧ

0.54

‎

0.54

 ComVisible

0.52

Activations Density 0.135%

terms related to scoring and performance metrics in a game context

No Comments

No Known Activations