INDEX

Explanations

references to coffee-related items and establishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ModelAdmin

-0.75

SpringBootTest

-0.73

AWG

-0.71

verwijspagina

-0.68

anyahu

-0.68

 Rahim

-0.68

)__

-0.67

__))

-0.65

 Lesnar

-0.64

AlterField

-0.63

POSITIVE LOGITS

 coffee

2.28

Coffee

2.08

 Coffee

2.06

coffee

2.06

 COFFEE

1.83

 coffees

1.83

 coffe

1.81

 Coffe

1.58

 kaffe

1.50

 espresso

1.49

Activations Density 0.063%

references to coffee-related items and establishments

No Comments

No Known Activations