INDEX

Explanations

functions and methods related to data processing and error handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

DataAnnotations

-0.58

prnewswire

-0.46

ANNOUNC

-0.45

ConstraintMaker

-0.42

 localObject

-0.40

 viewDidLoad

-0.39

-0.38

eroom

-0.38

KEYCODE

-0.37

 ExecuteAsync

-0.36

POSITIVE LOGITS

 يتيمه

0.91

الحياه

0.89

 مرئيه

0.81

 елның

0.72

 Paglinawan

0.72

 فريبيس

0.72

 bénévoles

0.71

 Chwiliwch

0.71

Hochspringen

0.70

 урна

0.68

Activations Density 0.391%

functions and methods related to data processing and error handling

No Comments

No Known Activations