INDEX

Explanations

references to kings and royalty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Travis

-0.66

 compri

-0.65

 Dars

-0.64

Travis

-0.63

 Prakash

-0.61

 apport

-0.60

Keefe

-0.59

 Quince

-0.58

__.

-0.57

 Lovato

-0.56

POSITIVE LOGITS

 Kings

1.39

 kings

1.32

 KING

1.23

 King

1.23

Kings

1.16

👑

1.12

 Koenig

1.10

 KINGS

1.09

 king

1.07

 monarch

1.06

Activations Density 0.145%

references to kings and royalty

No Comments

No Known Activations