INDEX

Explanations

references to the term "golden" and its variations in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DataMember

-0.70

uyasha

-0.69

 dequeue

-0.66

 Marcy

-0.65

skull

-0.65

Pob

-0.64

conceito

-0.63

OfWork

-0.63

scrub

-0.63

volezza

-0.62

POSITIVE LOGITS

 Golden

1.93

Golden

1.81

 golden

1.72

 GOLDEN

1.72

golden

1.66

ゴールデン

0.83

 Daley

0.82

 Cocker

0.80

 dorada

0.79

*{\

0.75

Activations Density 0.170%

references to the term "golden" and its variations in various contexts

No Comments

No Known Activations