INDEX

Explanations

names of scientific publications or authors associated with research

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

 esternos

-0.67

getDoctrine

-0.64

 surla

-0.56

 Executors

-0.52

MemoryWarning

-0.50

 ioutil

-0.47

Bibliographie

-0.42

myk

-0.42

AndEndTag

-0.42

 podjela

-0.41

POSITIVE LOGITS

 متعلقه

0.89

GEBURTSDATUM

0.81

archiviato

0.79

ksikon

0.74

 leſs

0.74

 ſta

0.74

 itſelf

0.74

 Reſ

0.72

 neceff

0.71

 purpoſe

0.69

Activations Density 1.639%

names of scientific publications or authors associated with research

No Comments

No Known Activations