INDEX

Explanations

references to criminal acts and the associated legal implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 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

uppa

-0.41

 Komunikasi

-0.39

 חיצוניים

-0.38

 Shimizu

-0.38

utusan

-0.38

ByteBuffer

-0.37

 Mehl

-0.37

 coach

-0.37

razor

-0.36

watch

-0.36

POSITIVE LOGITS

 crime

1.40

 crimes

1.30

crime

1.23

 Crime

1.19

 criminal

1.18

 CRIME

1.14

Crime

1.14

criminal

1.13

crimes

1.13

 criminality

1.08

Activations Density 0.461%

references to criminal acts and the associated legal implications

No Comments

No Known Activations