INDEX

Explanations

mathematical expressions and notations related to inequalities and limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 للمعارف

-0.56

 esternos

-0.52

 RESTRICT

-0.51

Bakgrunnsstoff

-0.50

iformis

-0.47

 Silly

-0.46

abus

-0.46

FORMA

-0.46

 scratch

-0.45

 ERSITY

-0.44

POSITIVE LOGITS

 rowspan

0.73

 poesía

0.58

 Lands

0.55

 thoroughly

0.54

 Offices

0.53

Lands

0.53

 lands

0.53

 poem

0.52

AnchorStyles

0.50

 poets

0.50

Activations Density 0.079%

mathematical expressions and notations related to inequalities and limits

No Comments

No Known Activations

mathematical expressions and notations related to inequalities and limits

No Comments

No Known Activations