INDEX

Explanations

terms associated with the mouth and oral health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

(;;)

-0.89

clerosis

-0.69

BCM

-0.68

tomans

-0.68

νι

-0.68

logram

-0.67

 secular

-0.67

 noble

-0.67

 escarp

-0.67

logrus

-0.67

POSITIVE LOGITS

 mouth

1.60

 Mouth

1.57

Mouth

1.42

 mouths

1.27

 lips

1.25

 Lips

1.24

mouth

1.21

 teeth

1.11

Lips

1.09

 Teeth

1.08

Activations Density 0.116%

terms associated with the mouth and oral health

No Comments

No Known Activations