INDEX

Explanations

numbers and their formatting in the text

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

})*/

-0.60

MLLoader

-0.56

ModelBuilder

-0.53

 صوتيه

-0.51

featureID

-0.51

saraba

-0.51

yym

-0.47

⋙

-0.47

ErrorListener

-0.46

TintMode

-0.46

POSITIVE LOGITS

GOTREF

0.55

Lähteet

0.52

حوالہ

0.43

 nakalista

0.42

 Legislative

0.41

 AssemblyCulture

0.40

 épices

0.39

 afternoon

0.38

 pomeriggio

0.38

Legislative

0.37

Activations Density 0.002%

numbers and their formatting in the text

No Comments

No Known Activations