INDEX

Explanations

occurrences of the term "label" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

will

-0.42

تقاوى

-0.41

 meisten

-0.41

Will

-0.40

vestre

-0.38

time

-0.37

 Mawr

-0.37

ukum

-0.37

 Will

-0.36

exp

-0.36

POSITIVE LOGITS

 Label

0.83

 LABEL

0.80

 jLabel

0.74

 label

0.71

 Labels

0.70

getLabel

0.70

ILabel

0.67

 labels

0.67

ViewImports

0.63

lbl

0.62

Activations Density 0.125%

occurrences of the term "label" across various contexts

No Comments

No Known Activations