INDEX

Explanations

prepositions indicating relationships or associations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Herodotus

-0.61

 cune

-0.60

MigrationBuilder

-0.58

 Sodom

-0.57

 Koran

-0.57

 hierogly

-0.57

 Osprey

-0.54

 panoramique

-0.54

 Boko

-0.54

 Mahabhar

-0.53

POSITIVE LOGITS

aarrggbb

0.65

 some

0.64

numel

0.61

GEBURTSDATUM

0.57

 ועל

0.56

 själva

0.56

daß

0.56

Statistiche

0.55

the

0.55

 many

0.54

Activations Density 0.270%

prepositions indicating relationships or associations

No Comments

No Known Activations