INDEX

Explanations

mentions of reality television shows and their related contests, judges, and participants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 sanitarias

-0.47

 sanitarios

-0.46

</strong>

-0.46

 aquela

-0.42

Lähteet

-0.42

/**

-0.38

to

-0.37

 لأن

-0.37

 esenciales

-0.37

些

-0.37

POSITIVE LOGITS

 themſelves

0.92

 betweenstory

0.90

 Jefus

0.89

PreferredItem

0.89

 myſelf

0.88

CodedInputStream

0.87

 Monfieur

0.86

 Housewives

0.86

ंदीखरीदारी

0.85

StructEnd

0.85

Activations Density 0.281%

mentions of reality television shows and their related contests, judges, and participants

No Comments

No Known Activations