INDEX

Explanations

references to the term "United" especially in the context of the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-2.71

Efq

-2.64

 itſelf

-2.64

 Anſ

-2.53

 Theſe

-2.52

 ―――――

-2.50

 Monfieur

-2.50

ſelf

-2.39

 Majefty

-2.38

 ſever

-2.36

POSITIVE LOGITS

1.66

1.41

1.39

<eos>

1.31

1.30

The

1.29

1.27

↵↵

1.27

Activations Density 0.369%

references to the term "United" especially in the context of the United States

No Comments

No Known Activations