INDEX

Explanations

references to vulnerable populations and their needs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 InputDecoration

-0.82

出版年

-0.74

Бележки

-0.72

 TextAppearance

-0.71

ThemeOverlay

-0.70

addContainerGap

-0.70

 Waray

-0.70

 defaultstate

-0.70

Datuak

-0.70

BeginContext

-0.69

POSITIVE LOGITS

 vulnerable

1.05

 Vulnerable

0.91

 vulnerability

0.83

 vulnerables

0.77

 Vulnerability

0.64

 vulnerabilities

0.64

nerable

0.61

 vulner

0.59

 vulné

0.59

vul

0.57

Activations Density 0.108%

references to vulnerable populations and their needs

No Comments

No Known Activations