INDEX

Explanations

mathematical symbols and notation related to probabilistic models and estimators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Meksiku

-0.63

Personensuche

-0.54

ABULARY

-0.52

TypedDataSet

-0.52

 estrenar

-0.50

AnchorTagHelper

-0.50

GeneratedMessage

-0.48

 municipale

-0.48

故

-0.48

emma

-0.47

POSITIVE LOGITS

mathrm

0.97

tagHelperRunner

0.88

évaluateur

0.80

AnchorStyles

0.73

GenerationType

0.68

getSystemService

0.67

NameInMap

0.64

 الرياضيه

0.63

__(/*!

0.57

참고

0.56

Activations Density 0.127%

mathematical symbols and notation related to probabilistic models and estimators

No Comments

No Known Activations