INDEX

Explanations

expressions of uncertainty or subjective opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

findpost

-0.82

abestanden

-0.81

 itſelf

-0.69

 мәкал

-0.69

Obrázky

-0.67

 Maho

-0.66

Efq

-0.64

OGND

-0.64

 Jefus

-0.64

 ویکی‌پدیای

-0.63

POSITIVE LOGITS

 because

1.16

due

1.00

because

0.94

 porque

0.89

 karena

0.86

Because

0.83

的原因

0.80

 потому

0.79

是因為

0.79

 Because

0.78

Activations Density 0.339%

expressions of uncertainty or subjective opinions

No Comments

No Known Activations