INDEX

Explanations

patterns in structured data or mathematical representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

存于互联网档案馆

-0.58

Facades

-0.56

 ویکی‌پدیای

-0.52

רצ

-0.50

 fallu

-0.50

fjspx

-0.50

 AttributeSet

-0.49

 manqué

-0.48

 staden

-0.47

 âgées

-0.47

POSITIVE LOGITS

 disambiguazione

0.78

verifyException

0.63

ValueStyle

0.61

ConstraintMaker

0.61

 الرياضيه

0.59

tableFuture

0.55

\{\\

0.55

 nakalista

0.53

SourceChecksum

0.52

Geplaatst

0.51

Activations Density 0.814%

patterns in structured data or mathematical representations

No Comments

No Known Activations