INDEX

Explanations

mentions of death and related statistics

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

preceding "died" or "death"

np_acts-logits-general · gemini-2.0-flash

died, death, or passed away

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

󠁢

-0.58

unzel

-0.54

 Bajos

-0.51

mány

-0.50

IBU

-0.50

్రామ

-0.48

ngrx

-0.46

ghorn

-0.46

 chande

-0.44

nestjs

-0.44

POSITIVE LOGITS

 died

2.64

 death

2.59

 deaths

2.24

death

2.23

 dying

2.10

 DEATH

2.01

 Death

2.01

Death

1.97

 dies

1.90

DEATH

1.88

Activations Density 0.687%

mentions of death and related statistics

preceding "died" or "death"

died, death, or passed away

No Comments

No Known Activations