INDEX

Explanations

occurrences of the word "Mad."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

styleType

-0.59

chymal

-0.56

Expedia

-0.52

 Investigaciones

-0.52

ailles

-0.51

醐

-0.46

Сюжет

-0.46

OneToOne

-0.45

oneph

-0.45

liferay

-0.45

POSITIVE LOGITS

GEBURTSDATUM

0.74

rigal

0.65

Personensuche

0.61

 متعلقه

0.61

 Hatter

0.58

onViewCreated

0.58

 onBind

0.57

 respeito

0.56

 Scientist

0.55

dox

0.55

Activations Density 0.254%

occurrences of the word "Mad."

No Comments

No Known Activations