INDEX

Explanations

prepositions and conjunctions that indicate relationships between entities in the text

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

in, by, of, from preceding other words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 recueil

-0.40

moveToFirst

-0.39

+:+

-0.38

 Biôgrafia

-0.36

tamment

-0.35

archiviato

-0.35

UpInside

-0.35

IFICACIONES

-0.34

 تكبرها

-0.33

RegistryLite

-0.33

POSITIVE LOGITS

verwijspagina

0.50

UrlResolution

0.49

BeginContext

0.45

Walk

0.44

didSet

0.44

 gentlemen

0.44

 يتيمه

0.44

principalColumn

0.43

abestanden

0.43

周泽

0.43

Activations Density 0.113%

prepositions and conjunctions that indicate relationships between entities in the text

in, by, of, from preceding other words

No Comments

No Known Activations