INDEX

Explanations

references to fame or well-known entities

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

脚注の使い方

-0.70

 envers

-0.67

TextInputLayout

-0.66

paksa

-0.63

AndEndTag

-0.63

 становника

-0.62

SBATCH

-0.61

 Parteien

-0.60

 Kigali

-0.60

 sembler

-0.59

POSITIVE LOGITS

 famous

2.83

famous

2.71

 Famous

2.59

Famous

2.50

 famoso

1.99

 famed

1.97

 famosa

1.96

 famosos

1.85

 berühmten

1.82

 renowned

1.78

Activations Density 0.085%

references to fame or well-known entities

No Comments

No Known Activations