INDEX

Explanations

references to "American" in any context

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

kháu

-1.01

 ComVisible

-0.91

 defaultstate

-0.91

 typelib

-0.86

 comigo

-0.83

 InputDecoration

-0.83

Hochspringen

-0.82

yntaxException

-0.82

 Pests

-0.79

 zipfile

-0.78

POSITIVE LOGITS

 American

2.93

American

2.75

 AMERICAN

2.35

AMERICAN

2.31

 american

2.29

american

2.26

 Americans

1.62

 Amerikan

1.57

 amerikanischen

1.48

 amerikan

1.43

Activations Density 0.043%

references to "American" in any context

No Comments

No Known Activations