INDEX

Explanations

code-related elements, specifically focusing on file uploads and their metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

runApp

-0.55

StructEnd

-0.53

eleste

-0.52

StoryboardSegue

-0.51

ngrx

-0.50

setVerticalGroup

-0.49

 biased

-0.48

 createContext

-0.47

 désactiv

-0.47

opardy

-0.46

POSITIVE LOGITS

 upload

1.86

 Upload

1.69

 uploading

1.66

 uploads

1.63

 uploaded

1.59

upload

1.59

Upload

1.56

Uploading

1.37

 file

1.37

UPLOAD

1.36

Activations Density 0.399%

code-related elements, specifically focusing on file uploads and their metadata

No Comments

No Known Activations