INDEX

Explanations

references to factors or elements that influence various outcomes or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

abetes

-0.86

原始内容存档于

-0.74

orgeous

-0.71

olulu

-0.69

edicated

-0.69

 onCreateView

-0.68

mime

-0.67

 Mahoney

-0.67

 libere

-0.67

Hyundai

-0.66

POSITIVE LOGITS

 factors

1.79

 Factors

1.73

factors

1.61

Factors

1.56

 Factor

1.55

 FACTOR

1.54

 FACTORS

1.52

 factor

1.45

Factor

1.42

factor

1.36

Activations Density 0.116%

references to factors or elements that influence various outcomes or behaviors

No Comments

No Known Activations