INDEX

Explanations

references to death and mortality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ništ

-0.97

tometer

-0.72

seguida

-0.68

 متحده

-0.68

GTS

-0.68

cheme

-0.67

Vea

-0.67

 wireType

-0.67

useppe

-0.67

WEBPACK

-0.67

POSITIVE LOGITS

 DEATH

1.15

 death

1.15

 deaths

1.09

DEATH

1.09

 Deaths

1.05

 Death

1.04

death

1.01

Death

0.98

 mourir

0.94

 śmier

0.91

Activations Density 0.121%

references to death and mortality

No Comments

No Known Activations