INDEX

Explanations

terms related to notifications and system interactions

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

UnusedPrivate

-0.51

 ब्रेकडाउन

-0.49

 detailsNormal

-0.48

vignon

-0.48

PerformLayout

-0.48

XmlAccessorType

-0.46

 autorytatywna

-0.46

providedIn

-0.45

 désolés

-0.43

 MainAxisSize

-0.42

POSITIVE LOGITS

expandindo

0.40

了嗎

0.40

 šķ

0.38

merz

0.37

ACHUSET

0.36

 elä

0.36

 uovo

0.35

แก

0.35

了吗

0.35

πό

0.35

Activations Density 0.103%

terms related to notifications and system interactions

No Comments

No Known Activations