INDEX

Explanations

references to physical objects or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

esModule

-0.51

culaire

-0.50

 متحده

-0.49

 utafitiHapana

-0.48

zyn

-0.48

 Xunit

-0.47

 Mugh

-0.46

Personensuche

-0.45

vants

-0.45

mixin

-0.44

POSITIVE LOGITS

aarrggbb

0.64

bukkit

0.56

 Lordships

0.55

 exemplaire

0.54

 exemplaires

0.54

 Réalisation

0.54

kkue

0.52

 copies

0.52

tanleria

0.52

copies

0.51

Activations Density 0.465%

references to physical objects or quantities

No Comments

No Known Activations