INDEX

Explanations

technical terms and components related to databases and programming constructs

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

ConstraintMaker

-0.66

SourceChecksum

-0.63

)";

-0.62

OOTDTY

-0.57

fillType

-0.56

Herzlich

-0.55

Enllaces

-0.54

.)}

-0.50

IsContent

-0.50

ReferenceEquals

-0.50

POSITIVE LOGITS

 alternate

0.77

 alternative

0.76

 another

0.75

 Alternative

0.73

 second

0.71

 Alternate

0.70

 Another

0.70

Alternate

0.70

 Plus

0.68

 alternates

0.66

Activations Density 0.613%

technical terms and components related to databases and programming constructs

No Comments

No Known Activations