INDEX

Explanations

words related to environmental and health risks from chemicals and pollutants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 bershka

-0.84

Efq

-0.82

 Jefus

-0.81

ſelf

-0.81

 moschino

-0.81

 Cæsar

-0.80

 Theſe

-0.79

 myſelf

-0.78

 greateſt

-0.77

WillAppear

-0.77

POSITIVE LOGITS

WireFormatLite

0.51

ixe

0.48

 AutoMapper

0.47

 anti

0.47

XmlAccessType

0.47

tocin

0.46

 مب

0.45

lactin

0.45

Activations Density 0.684%

words related to environmental and health risks from chemicals and pollutants

No Comments

No Known Activations