INDEX

Explanations

terms related to multiplicity or classification in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glTex

-0.43

 Spisak

-0.41

toplankton

-0.40

poken

-0.40

 Flamingo

-0.39

thasone

-0.38

Calais

-0.37

sistor

-0.37

 Alembic

-0.36

tisseur

-0.36

POSITIVE LOGITS

 multiple

1.02

Multiple

0.98

 MULTIPLE

0.98

multiple

0.97

 Multiple

0.95

MULTIPLE

0.88

 múltip

0.74

 múltiple

0.72

 múltiples

0.71

 resourceCulture

0.68

Activations Density 0.971%

terms related to multiplicity or classification in various contexts

No Comments

No Known Activations