INDEX

Explanations

references to sensors and sensing devices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 stea

-0.39

chemise

-0.38

bend

-0.36

squareup

-0.36

 isset

-0.36

 Bend

-0.35

intended

-0.34

sidemargin

-0.34

 Hòa

-0.34

 intended

-0.34

POSITIVE LOGITS

 sensor

0.90

 Sensor

0.83

 SENSOR

0.72

sensor

0.71

Sensor

0.69

ensor

0.68

 Normdatei

0.66

 sensors

0.65

tool

0.65

 Hardly

0.64

Activations Density 0.084%

references to sensors and sensing devices

No Comments

No Known Activations