INDEX

Explanations

references to collections and generics in code

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

MessageTagHelper

-0.60

 endwhile

-0.57

elemField

-0.53

 bại

-0.53

>(&

-0.52

SourceChecksum

-0.52

 Manley

-0.51

setUse

-0.51

 verte

-0.51

 diterima

-0.50

POSITIVE LOGITS

Generic

0.80

/**

0.72

enumi

0.70

ObjectModel

0.66

 للمعارف

0.65

########.

0.64

Specialized

0.58

 EconPapers

0.57

Diweddarwch

0.54

 Generic

0.54

Activations Density 0.035%

references to collections and generics in code

No Comments

No Known Activations