INDEX

Explanations

mentions of robots and robotic entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InstanceState

-0.76

 Montaigne

-0.70

醐

-0.69

 InputDecoration

-0.68

 Showers

-0.62

 senador

-0.62

Sass

-0.61

ALC

-0.61

EAR

-0.60

DOH

-0.60

POSITIVE LOGITS

 robot

2.18

 robots

2.08

 Robot

1.98

 Robots

1.93

robot

1.89

Robots

1.79

robots

1.79

Robot

1.72

 robotics

1.60

 robotic

1.59

Activations Density 0.101%

mentions of robots and robotic entities

No Comments

No Known Activations