INDEX

Explanations

names and terms related to specific individuals and scientific concepts

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

Leroy

-0.63

Nia

-0.62

Ler

-0.62

 BeautifulSoup

-0.61

 Leroy

-0.61

清

-0.58

 Morrison

-0.58

 boneless

-0.57

 bodyParser

-0.56

 cortes

-0.56

POSITIVE LOGITS

 Orrell

0.99

oughly

0.79

 Caribe

0.79

 Trist

0.77

complexContent

0.75

下载附件

0.74

onViewCreated

0.73

 Slov

0.71

yakit

0.68

agascar

0.67

Activations Density 2.144%

names and terms related to specific individuals and scientific concepts

No Comments

No Known Activations