INDEX

Explanations

topics related to acceleration and improvements in processes or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

hoid

-0.58

elemField

-0.58

MutableLiveData

-0.57

ripsi

-0.54

cosx

-0.54

typeparam

-0.54

 للاسماء

-0.54

 declarado

-0.50

 suena

-0.48

awsze

-0.48

POSITIVE LOGITS

 accelerated

1.36

 faster

1.27

 speeding

1.26

 sped

1.24

 speedy

1.24

 hurry

1.23

 speed

1.22

 fastest

1.22

faster

1.21

 hasten

1.20

Activations Density 0.390%

topics related to acceleration and improvements in processes or systems

No Comments

No Known Activations