INDEX

Explanations

mathematical symbols and notations used in defining sets and functions

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

protoimpl

-1.10

 propOrder

-0.81

onViewCreated

-0.80

featureID

-0.76

 AssemblyCulture

-0.76

InjectAttribute

-0.74

contentLoaded

-0.73

ViewFeatures

-0.73

WireFormat

-0.71

atrician

-0.70

POSITIVE LOGITS

mathcal

0.79

 Kell

0.53

igraphic

0.52

acchar

0.48

=[];

0.47

 بوك

0.47

 архивлан

0.47

pruch

0.47

 stehenden

0.46

χε

0.46

Activations Density 0.229%

mathematical symbols and notations used in defining sets and functions

No Comments

No Known Activations