INDEX

Explanations

relationships and connections between concepts or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

 nahilalakip

-0.49

Hochspringen

-0.48

Хьажоргаш

-0.43

ɵɵ

-0.43

Архівовано

-0.40

GEBURTSDATUM

-0.39

APORE

-0.38

WriteLiteral

-0.37

mbals

-0.37

eradish

-0.37

POSITIVE LOGITS

all

3.41

 semua

2.69

 kaikki

2.38

 todas

2.31

 wszystkie

2.30

 tutte

2.27

 wszystkich

2.17

 toate

2.13

 всех

2.11

 všechny

2.11

Activations Density 5.223%

relationships and connections between concepts or ideas

No Comments

No Known Activations