INDEX

Explanations

mentions of coffee and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

IsPostBack

-0.91

 AppModule

-0.83

وأضاف

-0.74

 Implements

-0.72

Kjelder

-0.70

 Navarre

-0.70

Ria

-0.69

 Վերցված

-0.68

 Cyril

-0.68

 Tipp

-0.68

POSITIVE LOGITS

 coffee

0.92

 Coffee

0.77

Coffee

0.76

coffee

0.74

 coffees

0.65

咖啡

0.62

 coffe

0.61

 COFFEE

0.59

 kaffe

0.57

コーヒー

0.56

Activations Density 0.045%

mentions of coffee and related concepts

No Comments

No Known Activations