INDEX

Explanations

phrases related to validation and evaluation in research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Protestantism

-0.62

 Roskov

-0.58

έχ

-0.58

setScene

-0.55

ंदीखरीदारी

-0.55

SearchParams

-0.54

 fevere

-0.54

tot

-0.53

 leſs

-0.53

 themſelves

-0.53

POSITIVE LOGITS

Fordítás

0.54

 مشين

0.50

出版年

0.47

akterysty

0.47

CppMethod

0.46

chmal

0.46

 tưởng

0.45

 indisponible

0.45

neapolis

0.45

 illustrate

0.45

Activations Density 0.653%

phrases related to validation and evaluation in research

No Comments

No Known Activations