INDEX

Explanations

mathematical labels and references in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 bodyParser

-0.71

 صوتيه

-0.67

 ModelExpression

-0.66

 FormData

-0.61

BOURNE

-0.61

sprzedam

-0.57

verwijspagina

-0.57

loß

-0.57

 AssemblyCulture

-0.57

angering

-0.56

POSITIVE LOGITS

 "..\..\..\

0.68

UnusedPrivate

0.65

 propOrder

0.64

eqnarray

0.63

section

0.60

ItemLayout

0.60

subsubsection

0.58

 "..\..\

0.58

GEBURTSDATUM

0.57

0.56

Activations Density 0.403%

mathematical labels and references in a document

No Comments

No Known Activations