INDEX

Explanations

phrases indicating a high frequency or quantity of something

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

出版年

-0.66

ématiques

-0.62

mybatisplus

-0.57

yelidikan

-0.53

 Autorizaciones

-0.53

 hObject

-0.51

moduleId

-0.51

UnusedPrivate

-0.50

aneously

-0.50

ómicas

-0.49

POSITIVE LOGITS

 respects

1.29

 cases

1.27

 ways

1.26

 instances

0.95

cases

0.90

 senses

0.90

 sentidos

0.87

 casos

0.85

 Fällen

0.84

 regards

0.82

Activations Density 0.358%

phrases indicating a high frequency or quantity of something

No Comments

No Known Activations