INDEX

Explanations

mathematical terms and expressions related to proofs and lemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

GOTREF

-0.58

">—

-0.52

 Normdatei

-0.52

WebElementEntity

-0.50

Hentet

-0.48

localctx

-0.47

xrTableCell

-0.47

tagext

-0.46

FlatList

-0.46

 oprot

-0.45

POSITIVE LOGITS

AnimationsModule

0.52

 parlant

0.40

 puder

0.40

 honneur

0.39

 acost

0.37

 maleta

0.37

 navideñas

0.37

 means

0.36

means

0.36

 geçmiş

0.36

Activations Density 0.202%

mathematical terms and expressions related to proofs and lemmas

No Comments

No Known Activations