INDEX

Explanations

terms and phrases related to interactions and interconnectivity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

toJson

-0.70

chtigkeit

-0.69

 تضيفلها

-0.65

<?>>

-0.65

 vouloir

-0.63

 bygga

-0.63

 Dati

-0.61

❯

-0.60

FormBuilder

-0.58

 clazz

-0.58

POSITIVE LOGITS

 INTER

1.36

 inter

1.31

INTER

1.23

 Inter

1.21

Inter

1.15

 interp

1.11

 Inters

1.09

 Interceptor

1.03

 inters

1.03

Inters

1.02

Activations Density 0.116%

terms and phrases related to interactions and interconnectivity in various contexts

No Comments

No Known Activations