INDEX

Explanations

variations of the word "happy."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

र्भ

-0.72

 мной

-0.72

 Borges

-0.70

 tehd

-0.69

 GenerationType

-0.68

hitheater

-0.67

 propOrder

-0.65

 Kelurahan

-0.65

 conducts

-0.64

ClientRect

-0.63

POSITIVE LOGITS

 happy

1.82

 Happy

1.77

 HAPPY

1.72

HAPPY

1.68

happy

1.59

Happy

1.56

 happiness

1.52

 happier

1.48

 Happiness

1.47

 HAPP

1.34

Activations Density 0.031%

variations of the word "happy."

No Comments

No Known Activations