INDEX

Explanations

references to editing roles or functions within a system

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

SequentialGroup

-1.00

 tartalomajánló

-0.98

ArrowToggle

-0.88

 <<<<<<<<<<<<<<

-0.84

NameInMap

-0.81



-0.81

 AppModule

-0.73

awaiter

-0.72

RegistryLite

-0.70

 utafitiHapana

-0.69

POSITIVE LOGITS

Editor

1.73

EDITOR

1.40

Editors

1.36

 Editor

1.22

 editing

1.21

 edit

1.19

Edit

1.19

edit

1.18

 Editors

1.16

 editors

1.13

Activations Density 0.240%

references to editing roles or functions within a system

No Comments

No Known Activations