INDEX

Explanations

repeated references to the word "young."

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

évaluateur

-0.76

 ActionListener

-0.75

 مرئيه

-0.71

 Obrador

-0.71

脚注の使い方

-0.70

 religieuses

-0.70

mantec

-0.69

 ویکی‌پدیا

-0.69

InteropServices

-0.67

ثيق

-0.66

POSITIVE LOGITS

 young

3.08

young

2.81

 Young

2.80

Young

2.79

 YOUNG

2.71

YOUNG

2.51

 younger

2.02

 Younger

1.91

 youthful

1.91

 jeune

1.90

Activations Density 0.048%

repeated references to the word "young."

No Comments

No Known Activations