INDEX

Explanations

terms related to research findings and methodologies

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

past tense scientific verbs followed by technical nouns

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 TestBed

-0.42

áng

-0.39

 cheval

-0.36

 stejně

-0.36

atán

-0.36

 someone

-0.35

XmlAccessorType

-0.34

ưỡi

-0.34

否

-0.34

ecm

-0.33

POSITIVE LOGITS

ंदीखरीदारी

0.59

 autorytatywna

0.54

 estekak

0.49

 насељу

0.48

getSystemService

0.47

 alapján

0.47

 transfieras

0.46

новништво

0.46

 Meksiku

0.45

 disponibilités

0.44

Activations Density 0.120%

terms related to research findings and methodologies

past tense scientific verbs followed by technical nouns

No Comments

No Known Activations