INDEX

Explanations

references to superiority or higher status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 normaux

-0.63

zetek

-0.61

 automatiques

-0.60

Біографія

-0.59

dims

-0.58

 bezpieczeństwa

-0.58

 veilig

-0.57

 manuelle

-0.57

 Hütte

-0.56

bildeten

-0.56

POSITIVE LOGITS

 nahilalakip

0.77

RepeatedField

0.67

principalTable

0.65

 betweenstory

0.64

पया

0.62

 Phase

0.61

AlterField

0.57

oredCriteria

0.57

 ostavi

0.57

StoryboardSegue

0.56

Activations Density 0.154%

references to superiority or higher status

No Comments

No Known Activations