INDEX

Explanations

details about modifications and adjustments in processes or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ImageContext

-0.66

AsUp

-0.56

 estekak

-0.55

 Audiodateien

-0.54

 StatefulWidget

-0.53

 Diſ

-0.53

createServer

-0.53

getSupport

-0.53

 Cæsar

-0.52

География

-0.51

POSITIVE LOGITS

########.

0.69

easeOut

0.60

 other

0.55

 iprot

0.52

 adaptées

0.52

 another

0.51

ambiar

0.50

ostro

0.50

 CreateTagHelper

0.49

ptes

0.49

Activations Density 0.623%

details about modifications and adjustments in processes or systems

No Comments

No Known Activations