INDEX

Explanations

references to killing or death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Altman

-0.82

 Himo

-0.81

theless

-0.77

 iNdEx

-0.76

 Folks

-0.69

dized

-0.67

Applicant

-0.67

 متحده

-0.65

>",

-0.65

 Manly

-0.64

POSITIVE LOGITS

 kill

2.03

 kills

1.94

 Kill

1.93

 KILL

1.93

kill

1.85

 killing

1.80

 killed

1.72

Kill

1.71

 Kills

1.71

KILL

1.69

Activations Density 0.049%

references to killing or death

No Comments

No Known Activations