INDEX

Explanations

references to prestigious institutions or organizations associated with "Royal."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Quince

-0.97

 Réponses

-0.96

RenderAtEndOf

-0.91

CCI

-0.87

 InputDecoration

-0.84

tanooga

-0.83

NSS

-0.80

 Brutus

-0.79

 Chattanooga

-0.77

ValueStyle

-0.76

POSITIVE LOGITS

 Royal

2.51

Royal

2.34

 royal

2.22

royal

2.20

 ROYAL

2.19

ROY

1.58

ロイヤル

1.55

 royals

1.47

 royale

1.42

 Royals

1.37

Activations Density 0.031%

references to prestigious institutions or organizations associated with "Royal."

No Comments

No Known Activations