INDEX

Explanations

references to ongoing tasks or projects

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

BibitemShut

-0.41

 mere

-0.33

ACIN

-0.31

Jîn

-0.31

 kaarangay

-0.31

achal

-0.30

ůž

-0.30

spect

-0.30

발

-0.28

Géographie

-0.28

POSITIVE LOGITS

 continues

0.76

 continue

0.73

continues

0.70

djangoproject

0.65

 EconPapers

0.65

Still

0.64

continue

0.64

 Still

0.63

 ſtill

0.63

 still

0.62

Activations Density 0.709%

references to ongoing tasks or projects

No Comments

No Known Activations