INDEX

Explanations

phrases indicating possession or specific references to objects or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

enumi

-0.98

tagHelperRunner

-0.89

 saites

-0.72

出版年

-0.70

AxisAlignment

-0.70

+#+#

-0.69

 الحره

-0.68

脚注の使い方

-0.67

 myself

-0.66

thâu

-0.64

POSITIVE LOGITS

 通販

0.54

 нужны

0.52

ftagPool

0.50

 нужен

0.48

 нужна

0.47

Need

0.47

בוד

0.46

 tarvit

0.46

 needed

0.46

 Италијани

0.45

Activations Density 0.122%

phrases indicating possession or specific references to objects or subjects

No Comments

No Known Activations