INDEX

Explanations

phrases related to instructions or actions

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

marle

-0.46

 yoksa

-0.44

UseVisualStyle

-0.43

 propOrder

-0.43

 tanım

-0.38

paravant

-0.38

subsubsection

-0.38

例文帳に追加

-0.37

ellipsis

-0.37

rigal

-0.37

POSITIVE LOGITS

Einfach

0.79

即可

0.73

 Basta

0.72

ArgsConstructor

0.72

 basta

0.71

 مشين

0.69

 wystarczy

0.69

 suffit

0.67

 Réponses

0.67

 Administrativna

0.67

Activations Density 0.186%

phrases related to instructions or actions

No Comments

No Known Activations