INDEX

Explanations

references to the name "Peter" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

<caption>

-0.61

ations

-0.55

 Reale

-0.55

setVerticalGroup

-0.54

 Shakspeare

-0.53

ussia

-0.53

 kentang

-0.53

 Monfieur

-0.53

 Reinhold

-0.53

 móvel

-0.52

POSITIVE LOGITS

 Peter

0.88

Peter

0.76

Clik

0.72

 PETER

0.72

peter

0.69

PETER

0.68

borough

0.63

 Infórmanos

0.61

 Peters

0.59

 peter

0.59

Activations Density 0.064%

references to the name "Peter" in various contexts

No Comments

No Known Activations