INDEX

Explanations

phrases related to local culinary experiences.

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

information related to various locations, including details about restaurants, cities, and local events.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases related to local experiences or interactions, particularly in the context of travel, dining, or cultural encounters.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

"local" or "locally"

np_acts-logits-general · gemini-2.0-flash

local residents and places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

########.

-0.56

Havolalar

-0.55

Spoljašnje

-0.53

 geslacht

-0.52

 незавершена

-0.52

/******/

-0.49

éda

-0.49

UnitTesting

-0.48

Bibliograf

-0.47

lappe

-0.47

POSITIVE LOGITS

 local

2.99

local

2.65

 locals

2.63

Local

2.48

 LOCAL

2.40

 Local

2.36

 locally

2.33

LOCAL

2.18

 lokale

2.14

 Locals

2.05

Activations Density 0.317%