INDEX

Explanations

numerals, particularly in the context of issues and identifiers within a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 NgModule

-0.74

webElement

-0.70

 '\\;'

-0.70

eradish

-0.67

 CreateTagHelper

-0.67

 ModelExpression

-0.63

➯

-0.60

 كومونز

-0.60

aarrggbb

-0.59

AntiForgeryToken

-0.57

POSITIVE LOGITS

↵↵

0.50

 دیکھیے

0.49

Lot

0.48

 heard

0.48

Искәрмәләр

0.48

<bos>

0.47

 بيها

0.47

 listened

0.46

گانه

0.46

 noticed

0.46

Activations Density 0.900%

numerals, particularly in the context of issues and identifiers within a structured format

No Comments

No Known Activations