INDEX

Explanations

references to rotation and rotational dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Jeanette

-0.78

 Meksiku

-0.77

 myco

-0.72

 doInBackground

-0.70

 McColl

-0.69

CDP

-0.69

➟

-0.67

inghouse

-0.66

الحياه

-0.65

saraba

-0.65

POSITIVE LOGITS

 rotations

1.39

 rotation

1.37

 rotates

1.35

 rotate

1.32

 spinning

1.27

 spins

1.27

 Rotation

1.26

Rotation

1.25

 rotated

1.24

 Spinning

1.18

Activations Density 0.274%

references to rotation and rotational dynamics

No Comments

No Known Activations