INDEX

Explanations

words and phrases related to taste and flavor in food

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

 فريبيس

-0.65

rangea

-0.60

šanās

-0.55

Cee

-0.52

Дереккөздер

-0.51

ódz

-0.51

 significant

-0.49

Cyfeiriadau

-0.48

rassed

-0.48

Msp

-0.47

POSITIVE LOGITS

 delicious

1.68

 tasting

1.57

 flavors

1.56

 Delicious

1.55

 tasted

1.52

 tasty

1.51

 flavor

1.50

 flavours

1.46

delicious

1.45

 Tasty

1.45

Activations Density 0.098%

words and phrases related to taste and flavor in food

No Comments

No Known Activations