INDEX

Explanations

elements related to advice or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 resourceCulture

-0.77

 Administrativna

-0.73

 conmigo

-0.72

ADELPHIA

-0.71

 Мексичка

-0.69

berdayakan

-0.68

 /\.(

-0.67

 Normdatei

-0.67

OGND

-0.67

 ProtoMessage

-0.67

POSITIVE LOGITS

 practically

0.46

 nawet

0.46

 буквально

0.46

甚至

0.45

Corresponding

0.45

)))

0.42

 через

0.42

шкой

0.42

 proprio

0.41

])),

0.41

Activations Density 0.010%

elements related to advice or recommendations

No Comments

No Known Activations