INDEX

Explanations

references to concentration camps and the context of World War II atrocities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 للاسماء

-0.46

 altid

-0.39

Rüyada

-0.39

ocino

-0.39

 AssemblyCulture

-0.38

出版年

-0.36

ereço

-0.35

Geplaatst

-0.35

 Freundin

-0.35

 Vierge

-0.35

POSITIVE LOGITS

 slave

0.60

locaust

0.58

Slave

0.57

 Slave

0.56

 slavery

0.55

slave

0.54

 prisoner

0.54

ValueStyle

0.53

Hochspringen

0.52

 Prisoner

0.52

Activations Density 0.529%

references to concentration camps and the context of World War II atrocities

No Comments

No Known Activations