INDEX

Explanations

references to magic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Portail

-0.57

setVerticalGroup

-0.55

complexContent

-0.51

MLLoader

-0.49

adult

-0.48

Adult

-0.48

John

-0.47

DockStyle

-0.46

Dome

-0.46

dome

-0.45

POSITIVE LOGITS

 magic

0.68

 Magic

0.60

magic

0.59

Magic

0.57

).

0.50

MAGIC

0.49

 capture

0.46

 MAGIC

0.45

 magically

0.42

 magical

0.42

Activations Density 0.168%

references to magic

No Comments

No Known Activations