INDEX

Explanations

references to locations, particularly related to Washington State and specific institutions in Seattle

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

rimidine

-0.55

Nassau

-0.54

jedis

-0.50

 اكتوبر

-0.50

PANY

-0.50

$_['

-0.49

 chi̍t

-0.48

 Chwiliwch

-0.47

UserRepository

-0.47

pad

-0.47

POSITIVE LOGITS

 Seattle

1.49

Seattle

1.36

 Puget

1.32

 Tacoma

1.21

 Spokane

1.11

seattle

1.08

 Yakima

0.94

 Bellingham

0.94

 Rainier

0.94

Sno

0.93

Activations Density 0.143%

references to locations, particularly related to Washington State and specific institutions in Seattle

No Comments

No Known Activations