INDEX

Explanations

terms related to labor and workforce dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 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

AsUp

-0.68

 Nieto

-0.67

homonymie

-0.65

cellona

-0.62

 Croft

-0.62

 outstretched

-0.61

 Murch

-0.59

sprogramm

-0.59

TestSuite

-0.59

 Pharisees

-0.58

POSITIVE LOGITS

 labor

3.53

 labour

3.15

 Labor

3.07

 LABOR

2.92

Labor

2.90

labor

2.78

 Labour

2.63

Labour

2.58

labour

2.57

 labors

2.25

Activations Density 0.065%

terms related to labor and workforce dynamics

No Comments

No Known Activations