INDEX

Explanations

specific keywords and parameters related to data extraction or processing within a programming or technical context

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

 garrafa

-0.44

 pamięci

-0.39

 silnika

-0.36

 hubieran

-0.36

 hjelp

-0.35

 falleció

-0.35

 cortesía

-0.34

 silnik

-0.34

 habrían

-0.33

 przód

-0.33

POSITIVE LOGITS

contentLoaded

0.61

featureID

0.60

 gyhoeddwyd

0.59

 AssemblyTitle

0.59

 HasFactory

0.58

 дописавши

0.57

[]){

0.56

 Италијани

0.55

ctl

0.54

getColumnIndex

0.54

Activations Density 1.743%

specific keywords and parameters related to data extraction or processing within a programming or technical context

No Comments

No Known Activations