INDEX

Explanations

instances and discussions of numerical measures of time and engagement in activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

Organisateur

-0.41

QMetaType

-0.35

oplayer

-0.35

 iNdEx

-0.35

Handlung

-0.34

cestor

-0.30

 تضيفلها

-0.29

ftagPool

-0.29

tiembre

-0.29

addCriterion

-0.29

POSITIVE LOGITS

 spent

1.07

 devoted

0.88

spent

0.84

 dedicated

0.80

 Spent

0.78

 away

0.76

 strá

0.73

 dedicado

0.70

 dedicada

0.70

 immersed

0.69

Activations Density 0.250%

instances and discussions of numerical measures of time and engagement in activities

No Comments

No Known Activations