INDEX

Explanations

tabular data elements and references within texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

archiviato

-0.50

 Вікіпе

-0.47

$\

-0.47

 Rowe

-0.46

medes

-0.45

-0.44

치

-0.44

way

-0.43

 Archiproducts

-0.43

ita

-0.42

POSITIVE LOGITS

 surla

0.84

IntoConstraints

0.77

Демографія

0.77

 kasarigan

0.76

 autorytatywna

0.74

 transférez

0.71

InitVars

0.71

GEBURTSDATUM

0.71

يكب

0.69

featureID

0.68

Activations Density 0.423%

tabular data elements and references within texts

No Comments

No Known Activations