INDEX

Explanations

references to specific measurements or variables related to research

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

RenderAtEndOf

-0.69

 تضيفلها

-0.66

ılıyor

-0.65

ıyordu

-0.62

ıştı

-0.60

ftagPool

-0.59

ırlar

-0.59

ंदीखरीदारी

-0.56

 Мексичка

-0.56

ıştır

-0.55

POSITIVE LOGITS

ma

2.87

MA

2.40

ma

1.81

MA

1.72

Ma

1.66

ма

1.55

Ma

1.51

МА

1.33

mas

1.31

maf

1.28

Activations Density 1.925%

references to specific measurements or variables related to research

No Comments

No Known Activations