INDEX

Explanations

terms related to vulnerability and at-risk populations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

InSection

-0.91

 المعيارى

-0.82

 صوتيه

-0.79

MessageOf

-0.78

 DialogInterface

-0.78

出版年

-0.74

LoadScene

-0.73

 refusé

-0.73

 Jaffe

-0.73

(!__

-0.72

POSITIVE LOGITS

 vulnerable

2.46

 vulnerability

2.23

 Vulnerable

2.21

nerable

1.97

 vulnerabilities

1.96

vul

1.90

 Vulnerability

1.89

 vulner

1.86

 vulnerables

1.79

Vul

1.73

Activations Density 0.068%

terms related to vulnerability and at-risk populations

No Comments

No Known Activations