INDEX

Explanations

references to the term "heavy"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Datuak

-0.85

:✨

-0.73

хьтан

-0.71

HtmlAttribute

-0.69

 виправивши

-0.68

AndEndTag

-0.67

XmlAccessorType

-0.67

 ویکی‌پدیای

-0.67

voorbeeld

-0.65

 propOrder

-0.64

POSITIVE LOGITS

 heavy

3.42

heavy

3.14

 Heavy

3.14

Heavy

3.09

 HEAVY

2.94

 heaviest

2.58

 heavier

2.48

 pesado

2.04

 heav

1.97

heav

1.94

Activations Density 0.034%

references to the term "heavy"

No Comments

No Known Activations