INDEX

Explanations

references to capital punishment and death-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

سطس

-0.72

 Assignee

-0.71

 bilinear

-0.71

complain

-0.71

pragma

-0.69

 Kami

-0.69

tôi

-0.68

 nonatomic

-0.68

gernaut

-0.68

cheme

-0.67

POSITIVE LOGITS

 death

1.83

 Death

1.75

 DEATH

1.73

death

1.64

DEATH

1.63

Death

1.63

 deaths

1.23

 Deaths

1.16

 muerte

1.15

 morte

1.13

Activations Density 0.120%

references to capital punishment and death-related contexts

No Comments

No Known Activations