INDEX

Explanations

references to coffee and related beverages

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

"coffee"

np_acts-logits-general · gemini-2.0-flash

coffee

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

othelioma

-0.43

 list

-0.41

 responsabilità

-0.40

 lists

-0.40

brigens

-0.39

 PublicKey

-0.38

 jsonArray

-0.38

 List

-0.37

 rôles

-0.37

 zdan

-0.36

POSITIVE LOGITS

 coffee

1.30

Coffee

1.22

coffee

1.20

 Coffee

1.18

 COFFEE

1.11

 koffie

1.07

 espresso

1.05

 coffe

1.05

 Kaffee

0.99

☕️

0.99

Activations Density 0.165%

references to coffee and related beverages

"coffee"

coffee

No Comments

No Known Activations