INDEX

Explanations

technical terms and jargon related to software development, particularly in cloud and platform services

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

脚注の使い方

-0.88

帖最后由

-0.85

InitVars

-0.81

rungsseite

-0.81

BufferException

-0.81

PropertyChanging

-0.80

новништво

-0.78

RTSC

-0.74

GeoNames

-0.72

 EconPapers

-0.70

POSITIVE LOGITS

apimachinery

0.88

kubernetes

0.78

 Kubernetes

0.68

Kubernetes

0.64

 kubernetes

0.63

kubectl

0.61

 metav

0.53

Kube

0.53

 kube

0.47

ectl

0.46

Activations Density 0.435%

technical terms and jargon related to software development, particularly in cloud and platform services

No Comments

No Known Activations