INDEX

Explanations

terms and concepts related to labor and its various contexts, such as employment 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 @ 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

smöglichkeiten

-0.85

glades

-0.81

 Thule

-0.80

 antlers

-0.79

 pickle

-0.75

cifix

-0.75

verläs

-0.75

 Merr

-0.74

 Gaylord

-0.74

 Clovis

-0.74

POSITIVE LOGITS

 Labor

1.45

 labor

1.43

labor

1.36

 LABOR

1.29

Labor

1.29

LABOR

1.24

 labors

1.19

 laboring

1.16

 labour

1.13

 Labour

1.06

Activations Density 0.134%

terms and concepts related to labor and its various contexts, such as employment and workforce dynamics

No Comments

No Known Activations