INDEX

Explanations

numerical values and data associated with specific metrics or identifiers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

月号

-0.52

 call

-0.50

 ostavi

-0.49

enheim

-0.49

 enti

-0.48

inderella

-0.47

TypeDef

-0.47

 חיצוניים

-0.47

xlarge

-0.47

Normdaten

-0.45

POSITIVE LOGITS

makeConstraints

0.78

enumi

0.75

 Yamato

0.74

 يتيمه

0.69

 MainAxisSize

0.67

CloseOperation

0.67

 Roskov

0.67

 AssemblyCompany

0.66

GEBURTSDATUM

0.64

 ―――――

0.63

Activations Density 0.081%

numerical values and data associated with specific metrics or identifiers

No Comments

No Known Activations