INDEX

Explanations

references to magic and magical concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-1.01

 Audiodateien

-0.83

RectangleBorder

-0.78

endsection

-0.74

IsContent

-0.74

principalColumn

-0.73

osoba

-0.72

ignoire

-0.71

*/].

-0.70

 Osprey

-0.69

POSITIVE LOGITS

 magic

2.40

 Magic

2.25

magic

2.21

Magic

2.16

 MAGIC

2.02

 magia

1.87

MAGIC

1.85

 magical

1.76

magical

1.61

 magique

1.49

Activations Density 0.067%

references to magic and magical concepts

No Comments

No Known Activations