INDEX

Explanations

mathematical symbols and equations related to labels and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

oa̍t

-0.65

complexContent

-0.47

تقاوى

-0.46

 surla

-0.44

XmlAccessorType

-0.43

ColumnHeaders

-0.43

감

-0.41

Utf

-0.41

 podjela

-0.40

encodeWith

-0.39

POSITIVE LOGITS

VersionUID

0.58

SuppressLint

0.54

 BoxFit

0.53

 nakalista

0.52

 AssemblyTitle

0.50

noinspection

0.42

subpackage

0.41

="#

0.39

TabIndex

0.39

AddTagHelper

0.37

Activations Density 0.931%

mathematical symbols and equations related to labels and definitions

No Comments

No Known Activations