INDEX

Explanations

details about coffee offerings and cafe features

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

before or related to "coffee"

np_acts-logits-general · gemini-2.0-flash

coffee and drinking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

riwal

-0.70

BindingResult

-0.60

 alimentaires

-0.58

ürtel

-0.58

 Reptile

-0.57

 Cabbage

-0.56

 Reptiles

-0.56

 fibrin

-0.55

 termites

-0.54

 Fische

-0.54

POSITIVE LOGITS

 coffee

1.86

 Coffee

1.55

coffee

1.51

Coffee

1.50

 coffees

1.48

 COFFEE

1.40

 espresso

1.40

 barista

1.34

 coffe

1.30

 caffeine

1.26

Activations Density 0.113%

details about coffee offerings and cafe features

before or related to "coffee"

coffee and drinking

No Comments

No Known Activations