INDEX

Explanations

expressions of enjoyment or positive experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ine

-0.67

Al

-0.61

Ber

-0.60

Hu

-0.58

Kle

-0.58

Ra

-0.58

netinet

-0.58

-0.57

pmatrix

-0.57

POSITIVE LOGITS

enjoy

1.88

 Enjoy

1.85

 enjoy

1.80

 ENJOY

1.76

 enjoyed

1.75

 enjoyment

1.69

Enjoying

1.68

Enjoy

1.66

 enjoys

1.63

 enjoying

1.60

Activations Density 0.037%

expressions of enjoyment or positive experiences

No Comments

No Known Activations