INDEX

Explanations

phrases related to causes and origins of events or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.74

VIAF

-0.73

 Catawiki

-0.62

 intptr

-0.60

ValueGeneration

-0.57

 propOrder

-0.57

 ChromeDriver

-0.57

 diagonally

-0.57

tagHelperRunner

-0.57

 binoculars

-0.54

POSITIVE LOGITS

хьтан

0.59

</thead>

0.55

GMENT

0.54

EndContext

0.53

DrawerToggle

0.53

hésite

0.53

 potential

0.52

 jopa

0.52

PERATURE

0.52

 duidelijk

0.48

Activations Density 0.384%

phrases related to causes and origins of events or conditions

No Comments

No Known Activations