INDEX

Explanations

tokens that indicate high importance or relevance, particularly in technical or systematic contexts

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

ValueStyle

-0.55

 informée

-0.52

 AspNetCore

-0.43

UrlResolution

-0.43

DataMember

-0.40

setupUi

-0.40

DataBinding

-0.38

 للمعارف

-0.37

нном

-0.37

WriteBarrier

-0.36

POSITIVE LOGITS

 resourceCulture

0.55

 Administrativna

0.50

StructEnd

0.49

icolon

0.45

 gynhyrchwyd

0.44

 Hatter

0.44

cipline

0.43

 հղումներ

0.42

 kasarigan

0.42

Personendaten

0.41

Activations Density 0.087%

tokens that indicate high importance or relevance, particularly in technical or systematic contexts

No Comments

No Known Activations