INDEX

Explanations

terms related to allegations and claims of wrongdoing

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 advocate

-0.68

advoc

-0.64

 bağlantılar

-0.62

 Castor

-0.61

ODS

-0.60

 posé

-0.60

 Thon

-0.59

 Flach

-0.59

്ട

-0.59

Huo

-0.58

POSITIVE LOGITS

 utilising

1.06

 utilised

1.01

 Utilizing

0.91

 utilise

0.91

 utilized

0.89

 utilizing

0.88

 utilisation

0.87

 alleges

0.86

 utilize

0.85

 Utilize

0.83

Activations Density 0.064%

terms related to allegations and claims of wrongdoing

No Comments

No Known Activations