INDEX

Explanations

proper nouns and significant details about individuals and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

 Administrativna

-0.73

majánló

-0.66

 estekak

-0.63

 Италијани

-0.62

httphttps

-0.60

Хьажоргаш

-0.58

 Roskov

-0.57

astéro

-0.56

horabuena

-0.56

cticut

-0.55

POSITIVE LOGITS

0.41

Mrs

0.38

()

0.35

Mrs

0.35

Mr

0.35

$\

0.35

[]

0.34

 Survivors

0.34

ms

0.34

currentColor

0.34

Activations Density 0.052%

proper nouns and significant details about individuals and their relationships

No Comments

No Known Activations