INDEX

Explanations

references to North Korea and its leaders

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

mergeFrom

-0.48

HasAnnotation

-0.48

CreateIndex

-0.42

differential

-0.41

AFS

-0.39

bnf

-0.38

 differential

-0.38

BNF

-0.37

kloped

-0.37

 lavable

-0.37

POSITIVE LOGITS

 Pyongyang

1.06

 North

0.97

North

0.90

DPR

0.89

Kim

0.81

Kim

0.75

Py

0.71

 NORTH

0.70

 Korean

0.66

朝鲜

0.62

Activations Density 0.208%

references to North Korea and its leaders

No Known Activations