INDEX

Explanations

phrases related to evaluation and outcomes

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

exitRule

-0.54

 հղումներ

-0.51

 gratuites

-0.49

usy

-0.49

annia

-0.49

 dramatique

-0.46

 AttributeSet

-0.44

retweeted

-0.43

 gratuits

-0.43

 peix

-0.42

POSITIVE LOGITS

 betweenstory

0.76

 дописавши

0.75

 beginnetje

0.71

 يتيمه

0.67

 Мексичка

0.65

 ویکی‌پدیای

0.64

]")]

0.64

 nonUne

0.62

 ModelExpression

0.62

 PhpStorm

0.61

Activations Density 1.124%

phrases related to evaluation and outcomes

No Comments

No Known Activations