INDEX

Explanations

concepts related to efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

:✨

-0.53

InputBorder

-0.50

 المعيارى

-0.46

 autorytatywna

-0.45

GEBURTSDATUM

-0.45

limiento

-0.43

uestamente

-0.43

clerView

-0.42

fetchone

-0.42

 SqlConnection

-0.41

POSITIVE LOGITS

 Trade

0.61

argout

0.52

المناصب

0.50

.*")]

0.50

isticated

0.47

enumi

0.47

Trade

0.45

sack

0.44

)‏

0.44

大事

0.44

Activations Density 0.345%

concepts related to efficiency

No Comments

No Known Activations