INDEX

Explanations

phrases related to specific locations and environmental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

tober

-0.51

 deuil

-0.50

couvrir

-0.48

かわらず

-0.47

ervious

-0.47

MLLoader

-0.46

//});

-0.46

uname

-0.46

óta

-0.45

chitis

-0.45

POSITIVE LOGITS

 location

1.07

 where

0.97

 locations

0.92

where

0.90

 Location

0.86

 locatie

0.85

location

0.84

 Where

0.83

Where

0.80

 lokasi

0.79

Activations Density 0.640%

phrases related to specific locations and environmental contexts

No Comments

No Known Activations