INDEX

Explanations

concepts related to inquiries and evaluations in various contexts

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

preceding "solution," "properties," "idea," "case," etc

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

Sklici

-0.54

 Wikiseite

-0.49

 izquier

-0.47

 autorytatywna

-0.47

:✨

-0.47

nezeu

-0.47

clusal

-0.45

 Lieben

-0.44

Выводы

-0.44

colgante

-0.43

POSITIVE LOGITS

BeginInit

0.49

 AttributeSet

0.48

IContainer

0.47

 ModelExpression

0.46

 InputDecoration

0.43

ⓧ

0.43

Portail

0.41

ParallelGroup

0.41

存于互联网档案馆

0.40

󠁴

0.39

Activations Density 0.805%

concepts related to inquiries and evaluations in various contexts

preceding "solution," "properties," "idea," "case," etc

No Comments

No Known Activations