INDEX

Explanations

mathematical notations and symbols related to statistical models and data representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 urbanas

-0.54

 humanas

-0.54

 formales

-0.52

MethodManager

-0.50

 médicas

-0.49

 Grèce

-0.48

 geométrico

-0.46

него

-0.45

and

-0.45

 científicas

-0.45

POSITIVE LOGITS

 initComponents

0.84

 مرئيه

0.79

0.75

 ProtoMessage

0.73

 Савезне

0.73

LookAnd

0.73

 >=",

0.72

Datuak

0.72

encodeWith

0.71

GraphicsUnit

0.69

Activations Density 0.407%

mathematical notations and symbols related to statistical models and data representation

No Comments

No Known Activations