INDEX

Explanations

mathematical notations and symbols related to functions and sequences in a formal context

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

 arşivlendi

-0.58

 архивлан

-0.58

Gizmos

-0.57

 StatefulWidget

-0.52

CURLOPT

-0.50

InputBorder

-0.49

 Walkover

-0.48

netics

-0.48

 Administrativna

-0.47

 CURIAM

-0.47

POSITIVE LOGITS

]=>

0.60

 '\\;'

0.58

Clik

0.52

ipel

0.52

marshaller

0.51

WriteTagHelper

0.51

ThemeOverlay

0.50

NamedQueries

0.50

CppMethod

0.48

 ProtoMessage

0.48

Activations Density 0.686%

mathematical notations and symbols related to functions and sequences in a formal context

No Comments

No Known Activations