INDEX

Explanations

phrases indicating the world's ranking or status in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

XtraGrid

-0.55

berater

-0.48

下载附件

-0.48

unmodifiable

-0.48

niająca

-0.48

 Tulane

-0.45

paren

-0.45

 rodo

-0.45

 provinciale

-0.44

makeConstraints

-0.44

POSITIVE LOGITS

+#+#

0.82

はじめに

0.77

 AssemblyTitle

0.76

ÑOS

0.75

PMailer

0.73

 largest

0.67

 مرئيه

0.66

+#+

0.66

agy

0.64

emed

0.64

Activations Density 0.064%

phrases indicating the world's ranking or status in various contexts

No Comments

No Known Activations