INDEX

Explanations

references to the term "Bon," particularly in various contexts or related terms

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

currentColor

-0.48

 negative

-0.48

tonsoft

-0.48

PathVariable

-0.47

徊

-0.47

ństwa

-0.46

 vulgaires

-0.46

 Negative

-0.46

 yên

-0.45

ful

-0.45

POSITIVE LOGITS

Bon

0.84

BON

0.80

bon

0.79

Bon

0.79

 désolés

0.78

ItemBackground

0.76

bon

0.73

BON

0.72

bons

0.71

]")]

0.70

Activations Density 0.072%

references to the term "Bon," particularly in various contexts or related terms

No Comments

No Known Activations