INDEX

Explanations

references to the word "Bo" or variations of it, including its usage in names and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Twit

-0.94

 Reiche

-0.94

 Mede

-0.93

 AppColors

-0.91

})));

-0.90

Kuz

-0.89

 CrossRef

-0.88

 pleaſure

-0.88

jmniej

-0.87

 Ural

-0.86

POSITIVE LOGITS

bo

1.21

Bo

1.21

Bo

1.07

bo

1.01

BO

0.94

 BOAT

0.92

 Boeh

0.91

BO

0.90

 boats

0.84

 Boats

0.82

Activations Density 0.228%

references to the word "Bo" or variations of it, including its usage in names and products

No Comments

No Known Activations