INDEX

Explanations

people's names and their roles or titles

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

 تضيفلها

-0.87

 Baillargeon

-0.63

wpi

-0.57

ISupport

-0.53

ξει

-0.53

 imageNamed

-0.53

RTLD

-0.52

 ***!

-0.52

 Allociné

-0.51

 EconPapers

-0.51

POSITIVE LOGITS

SourceChecksum

0.60

complexType

0.51

;"><

0.50

 برگ

0.47

oredCriteria

0.46

0.44

 Guest

0.43

 Weltkrieg

0.42

‘

0.41

Activations Density 0.089%

people's names and their roles or titles

No Comments

No Known Activations