INDEX

Explanations

terms related to data type definitions and programming constructs in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

出版年

-0.40

(&:

-0.38

 paramInt

-0.36

NewLabel

-0.35

 voici

-0.34

स्था

-0.33

 IndexError

-0.33

 hwnd

-0.32

ához

-0.32

 AssemblyProduct

-0.32

POSITIVE LOGITS

0.60

 Normdatei

0.57

0.50

 مرئيه

0.48

Personendaten

0.47

IBOutlet

0.46

IntoConstraints

0.45

ReusableCell

0.44

 agrí

0.44

HtmlAttribute

0.43

Activations Density 0.409%

terms related to data type definitions and programming constructs in code

No Comments

No Known Activations