INDEX

Explanations

terms related to health metrics and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 disambiguazione

-0.70

 AssemblyCompany

-0.70

OGND

-0.68

⟬

-0.65

PreInfinity

-0.64

WithMany

-0.63

MigrationBuilder

-0.63

sizeCache

-0.63

лтемелер

-0.63

SharedDtor

-0.63

POSITIVE LOGITS

is

1.33

has

1.20

was

1.02

 becomes

0.92

isn

0.90

can

0.87

 will

0.87

 doesn

0.86

 goes

0.86

 gets

0.86

Activations Density 1.890%

terms related to health metrics and evaluations

No Comments

No Known Activations