INDEX

Explanations

elements of JSON schemas, particularly focusing on data types and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

adaptiveStyles

-0.81

 Administrativna

-0.80

 виправивши

-0.79

 вікі

-0.75

]){

-0.75

хьтан

-0.71

 informée

-0.70

])),

-0.69

 насељу

-0.68

IVEREF

-0.65

POSITIVE LOGITS

AxisAlignment

0.63

piac

0.53

atilde

0.52

 viewDidLoad

0.51

VersionUID

0.49

 étudi

0.49

 Evangelio

0.48

 doInBackground

0.48

wpi

0.48

ñora

0.47

Activations Density 0.302%

elements of JSON schemas, particularly focusing on data types and attributes

No Comments

No Known Activations