INDEX

Explanations

references to labor exploitation, particularly in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 VIDEOTAPE

-0.68

RetentionPolicy

-0.57

MemoryWarning

-0.56

RTLR

-0.55

sizeCache

-0.53

RUnlock

-0.50

İstinadlar

-0.50

ResponseWriter

-0.49

Viitteet

-0.49

AutoresizingMask

-0.49

POSITIVE LOGITS

 labor

1.30

 labour

1.29

 worker

1.23

 laborers

1.21

 laborer

1.17

 workers

1.16

 labourers

1.11

 work

1.08

labour

1.08

 labourer

1.07

Activations Density 0.396%

references to labor exploitation, particularly in historical contexts

No Comments

No Known Activations