INDEX

Explanations

representations of class definitions and object attributes in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Datuak

-0.67

GOTREF

-0.64

DoubleQuotes

-0.58

KommentareTeilen

-0.57

 مشين

-0.54

($__

-0.53

ViewImports

-0.53

MLLoader

-0.51

AndEndTag

-0.51

"]();

-0.51

POSITIVE LOGITS

 disambiguazione

0.56

,*

0.53

TemporalType

0.52

Hentet

0.49

<?

0.44

self

0.44

izaje

0.43

lecular

0.43

 Clears

0.43

луй

0.42

Activations Density 0.118%

representations of class definitions and object attributes in code

No Comments

No Known Activations