INDEX

Explanations

instances of the word "and" as well as related phrases indicating connections or relationships

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

"and" preceding a noun

np_acts-logits-general · gemini-2.0-flash

lists connected concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

memberof

-0.33

kolle

-0.30

 cabinet

-0.28

 summer

-0.28

Jou

-0.27

me

-0.27

 createSprite

-0.26

 COLLE

-0.26

rou

-0.26

old

-0.26

POSITIVE LOGITS

 Infórmanos

0.73

abstractmethod

0.69

 initComponents

0.66

ModelSerializer

0.66

 Pardavimas

0.65

linawan

0.65

الحياه

0.64

writeFieldEnd

0.64

ſehen

0.63

EndInit

0.63

Activations Density 0.730%

instances of the word "and" as well as related phrases indicating connections or relationships

"and" preceding a noun

lists connected concepts

No Comments

No Known Activations