INDEX

Explanations

geographical locations and names, particularly related to New York City

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 useContext

-0.60

 zirconium

-0.60

 Obispo

-0.57

posedge

-0.57

 nakalista

-0.53

RequestMapping

-0.52

nocache

-0.51

ำ

-0.50

 Euphrates

-0.50

ixar

-0.49

POSITIVE LOGITS

NYC

1.25

NYC

1.17

 Brooklyn

1.01

 Bronx

1.00

 Manhattan

1.00

 Amsterdam

0.96

 Toronto

0.96

nyc

0.94

 Mumbai

0.94

Mumbai

0.91

Activations Density 0.907%

geographical locations and names, particularly related to New York City

No Comments

No Known Activations