INDEX

Explanations

terms related to robotics and robotic systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Summa

-0.77

 Koss

-0.70

 Montaigne

-0.69

spira

-0.69

 Lorentz

-0.68

UnsafeEnabled

-0.68

aires

-0.67

oke

-0.67

vaadin

-0.66

 Addison

-0.65

POSITIVE LOGITS

 robot

1.54

 robots

1.50

 Robot

1.43

 Robots

1.38

obot

1.28

robot

1.26

Robots

1.25

Robot

1.24

 robotics

1.20

robots

1.20

Activations Density 0.103%

terms related to robotics and robotic systems

No Comments

No Known Activations