INDEX

Explanations

phrases that express strong recommendations or endorsements

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

"])

-0.50

sequelize

-0.49

 Rudi

-0.49

printLine

-0.48

 }}}{

-0.48

Clik

-0.48

)‏

-0.48

цездатний

-0.47

'},

-0.47

tése

-0.47

POSITIVE LOGITS

 kasarigan

0.77

 рекомендую

0.71

 متعلقه

0.69

enswert

0.61

 recommande

0.59

Polecam

0.57

 propOrder

0.56

Definitely

0.52

 conseille

0.52

MUST

0.52

Activations Density 0.181%

phrases that express strong recommendations or endorsements

No Comments

No Known Activations