INDEX

Explanations

words related to labor and social class, sometimes with a focus on women's work

oai_token-act-pair · gemini-2.0-flash

factory workers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RetentionPolicy

-0.70

 GenerationType

-0.65

المشاركات

-0.63

 CascadeType

-0.63

 BorderRadius

-0.60

IntoConstraints

-0.60

abestanden

-0.59

 actionTypes

-0.57

findpost

-0.57

ⓧ

-0.56

POSITIVE LOGITS

 factory

1.32

 workers

1.25

 worker

1.18

 Factory

1.12

 factories

1.09

 industrial

1.07

 labor

1.05

 laborers

1.05

factory

1.04

 Workers

1.04

Activations Density 3.917%

words related to labor and social class, sometimes with a focus on women's work

factory workers

No Comments

No Known Activations