INDEX

Explanations

references to developer documentation and code samples related to software and APIs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ModelAdmin

-0.71

MessageOf

-0.56

 Sebasti

-0.53

 secolo

-0.51

viewDidLoad

-0.51

衛門

-0.50

 reciclado

-0.49

Obrázky

-0.49

 silvestre

-0.49

 հղումներ

-0.48

POSITIVE LOGITS

 linkovi

0.67

 uska

0.53

Autoritní

0.52

 تانيه

0.51

adpleegd

0.50

KommentareTeilen

0.49

IUrlHelper

0.49

 Meksiku

0.49

endous

0.48

 AssemblyCulture

0.48

Activations Density 0.411%

references to developer documentation and code samples related to software and APIs

No Comments

No Known Activations