INDEX

Explanations

terms related to homicide and murder-related offenses

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Eck

-0.62

rinfo

-0.60

Gos

-0.58

 fair

-0.56

acchar

-0.55

 vouch

-0.54

cheme

-0.53

 Circa

-0.53

Cog

-0.52

appy

-0.52

POSITIVE LOGITS

 killing

1.62

 killed

1.57

 kill

1.56

 murder

1.55

 murders

1.55

 kills

1.53

 killings

1.48

 murdered

1.43

murder

1.41

 murdering

1.40

Activations Density 0.186%

terms related to homicide and murder-related offenses

No Known Activations