INDEX

Explanations

phrases related to contextual frameworks and settings in scientific discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 myſelf

-0.95

 uſed

-0.93

 himſelf

-0.89

 Majefty

-0.88

 ſeveral

-0.88

 ſta

-0.87

 ſaid

-0.86

 Jefus

-0.86

 houſe

-0.86

 ſtate

-0.85

POSITIVE LOGITS

PreferredItem

0.69

ernalia

0.65

Abitanti

0.64

withIdentifier

0.64

GEBURTSDATUM

0.62

脚注の使い方

0.62

例文帳に追加

0.61

 оригіналу

0.60

Tembelea

0.59

Portale

0.58

Activations Density 0.426%

phrases related to contextual frameworks and settings in scientific discourse

No Comments

No Known Activations