INDEX

Explanations

terms related to employment, labor force participation, wages, job creation, and economic impact

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

djangoproject

-0.50

WebServlet

-0.49

 autorytatywna

-0.47

 lép

-0.45

ifilm

-0.45

 défi

-0.43

참고

-0.42

effectiveness

-0.42

 operazioni

-0.42

parsedMessage

-0.41

POSITIVE LOGITS

 Employment

1.32

 employment

1.28

Employment

1.26

 EMPLOYMENT

1.16

employment

1.09

 unemployment

1.06

 jobs

1.05

 laboral

1.05

 Unemployment

1.05

 employers

1.02

Activations Density 0.464%

terms related to employment, labor force participation, wages, job creation, and economic impact

No Comments

No Known Activations