INDEX

Explanations

both markup or programming-related syntax and numerical data

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

heiser

-0.53

lendir

-0.51

BindingSource

-0.50

出自

-0.49

 کنیم

-0.49

 struct

-0.49

 MERCHANTABILITY

-0.49

CUSS

-0.47

Dono

-0.46

 writeTo

-0.46

POSITIVE LOGITS

DispatchToProps

0.64

ImageContext

0.61

ⓧ

0.61

RefNanny

0.60

 ModelExpression

0.60

AnimationsModule

0.56

 Legendre

0.54

ByVersion

0.52

 متعلقه

0.52

PreferredItem

0.51

Activations Density 0.411%

both markup or programming-related syntax and numerical data

No Comments

No Known Activations