INDEX

Explanations

phrases that indicate duration or time measurements related to experiences or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

/**

-0.65

 Bourgoin

-0.60

//

-0.52

smallest

-0.51

ToScroll

-0.49

 wisatawan

-0.49

 pilgrims

-0.49

 CreateTagHelper

-0.48

XmlType

-0.48

ObjectModel

-0.48

POSITIVE LOGITS

 nonstop

0.76

++

0.75

 continual

0.71

)++;

0.71

Endless

0.71

setupUi

0.70

 TimeUnit

0.70

 relentless

0.70

"%(

0.69

olesale

0.69

Activations Density 0.083%

phrases that indicate duration or time measurements related to experiences or activities

No Comments

No Known Activations