INDEX

Explanations

instances of specific identifiers or tags in technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 الحره

-0.38

zzleHttp

-0.32

LabelTagHelper

-0.32

 Projektu

-0.30

 enter

-0.28

ioe

-0.27

():

-0.26

 poorly

-0.26

"){

-0.26

(){

-0.26

POSITIVE LOGITS

 AssemblyCompany

0.71

mbggenerated

0.66

RegistryLite

0.62

новниш

0.60

 surla

0.57

#+#

0.56

MENAFN

0.55

 kasarigan

0.53

 nahilalakip

0.53

Obrázky

0.52

Activations Density 0.651%

instances of specific identifiers or tags in technical documentation

No Comments

No Known Activations