INDEX

Explanations

phrases indicating actions or decisions made by individuals or groups

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

Cechy

-0.42

 resourceCulture

-0.38

tagHelperRunner

-0.38

tificates

-0.37

Gap

-0.37

ifers

-0.37

 Umständen

-0.36

 Konk

-0.36

sproz

-0.36

izza

-0.36

POSITIVE LOGITS

 propOrder

0.48

лтемелер

0.47

interopRequire

0.46

DockStyle

0.43

ThroughAttribute

0.43

 StatelessWidget

0.42

 CanadaChoose

0.42

 erfaring

0.42

 responsabilità

0.40

æng

0.40

Activations Density 0.169%

phrases indicating actions or decisions made by individuals or groups

No Comments

No Known Activations