INDEX

Explanations

references to various types of sensors and their applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 ainfi

-0.65

RTEX

-0.65

 feroit

-0.64

 Geiſt

-0.63

ſſung

-0.63

 avoient

-0.63

 plufieurs

-0.62

<unused43>

-0.62

<unused23>

-0.61

<unused17>

-0.61

POSITIVE LOGITS

 sensor

1.22

sensor

1.05

 sensors

0.91

 Sensor

0.86

Sensor

0.75

 sensing

0.75

 SENSOR

0.69

 sens

0.66

sensors

0.65

SENSOR

0.65

Activations Density 0.276%

references to various types of sensors and their applications

No Comments

No Known Activations