INDEX

Explanations

references to educational qualifications and levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

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

setopt

-0.50

rects

-0.40

LEncoder

-0.39

aller

-0.38

StoryboardSegue

-0.37

offsetTop

-0.36

otoro

-0.36

 transfieras

-0.35

allocate

-0.35

UnitTesting

-0.35

POSITIVE LOGITS

 disambiguazione

0.58

 autorytatywna

0.58

OGND

0.57

 Reverso

0.51

 ujednoznacz

0.50

 bénévoles

0.47

ništ

0.47

Tembelea

0.46

ImageContext

0.46

 Normdatei

0.46

Activations Density 0.014%

references to educational qualifications and levels

No Comments

No Known Activations