INDEX

Explanations

technical terms and phrases related to research publications and their metrics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 munc

-0.47

γει

-0.47

 GBIF

-0.47

CMP

-0.46

fige

-0.46

Panel

-0.43

 toute

-0.42

 Dernière

-0.41

毙

-0.39

us

-0.39

POSITIVE LOGITS

ioutil

1.01

حوالہ

0.88

 nahilalakip

0.86

Bronnen

0.71

Jegyzetek

0.71

ειτουργ

0.71

المراجع

0.70

Παραπομπές

0.70

таратура

0.69

مراجع

0.68

Activations Density 6.883%

technical terms and phrases related to research publications and their metrics

No Comments

No Known Activations