INDEX

Explanations

comparative adjectives indicating size, speed, and weight

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

-0.80

-0.73

-0.72

mit

-0.72

Go

-0.69

Ar

-0.68

Al

-0.67

POSITIVE LOGITS

 leſs

1.88

 myſelf

1.65

 happier

1.54

 healthier

1.52

 shallo

1.51

 easier

1.51

 quieter

1.50

 thicker

1.50

 thinner

1.50

 heavier

1.50

Activations Density 0.164%

comparative adjectives indicating size, speed, and weight

No Comments

No Known Activations