INDEX

Explanations

references to code or programming concepts within technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Zacks

-0.59

 Hirsch

-0.45

 cannon

-0.45

^*)

-0.43

Zacks

-0.43

ディダス

-0.43

 matériel

-0.42

Mileage

-0.41

วรร

-0.41

Throwaway

-0.41

POSITIVE LOGITS

SourceChecksum

0.86

 resourceCulture

0.85

rrggbb

0.74

RegistryLite

0.74

Portail

0.73

 فريبيس

0.70

NameInMap

0.66

 BoxFit

0.66

styleType

0.66

esez

0.65

Activations Density 0.391%

references to code or programming concepts within technical documentation

No Comments

No Known Activations