INDEX

Explanations

prepositions and indicators of relationships between entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 kaarangay

-0.47

uxxxx

-0.46

мәләр

-0.44

Publica

-0.44

 knock

-0.42

 compactness

-0.41

ۗ

-0.41

 juggling

-0.41

 strop

-0.41

 paink

-0.41

POSITIVE LOGITS

TargetException

0.49

 AssemblyProduct

0.49

 continúas

0.47

httphttps

0.45

AnimationsModule

0.44

GOTREF

0.43

Hauptartikel

0.41

(!__

0.41

 ویکی‌پدیای

0.40

reactstrap

0.40

Activations Density 0.541%

prepositions and indicators of relationships between entities or concepts

No Comments

No Known Activations