INDEX

Explanations

technical terms and numerical identifiers related to encryption and computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ftagPool

-0.75

ponses

-0.64

bidden

-0.64

)))));

-0.64

getWriter

-0.64

)\}

-0.60

clo

-0.59

forName

-0.58

riss

-0.58

 pousse

-0.57

POSITIVE LOGITS

 متعلقه

0.74

GEBURTSDATUM

0.73

MessageOf

0.73

rrggbb

0.69

webElementGuid

0.66

Diweddarwch

0.63

 AspNetCore

0.62

Rujuakan

0.59

makeConstraints

0.57

 ISNI

0.55

Activations Density 1.573%

technical terms and numerical identifiers related to encryption and computing

No Comments

No Known Activations