INDEX

Explanations

references to slave ownership and the context surrounding it

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

slavery and slaves

np_acts-logits-general · gemini-2.0-flash

owned slaves and/or slavery

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

庁

-0.55

Hochspringen

-0.55

TestingModule

-0.54

RD

-0.54

Viki

-0.54

 kesi

-0.52

Naissance

-0.52

出版年

-0.52

 mété

-0.52

 Schützen

-0.51

POSITIVE LOGITS

 slave

1.70

 slaves

1.53

 slavery

1.47

 Slave

1.46

slave

1.44

 enslaved

1.40

Slave

1.36

 Slavery

1.28

 Slaves

1.25

 escla

1.23

Activations Density 0.335%

references to slave ownership and the context surrounding it

slavery and slaves

owned slaves and/or slavery

No Comments

No Known Activations