INDEX

Explanations

phrases that indicate items or elements being enumerated or specified

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

JNIEnv

-0.66

tagHelperRunner

-0.64

 otomatig

-0.63

 pellets

-0.63

 कैसी

-0.63

 Paradis

-0.60

Искәрмәләр

-0.60

mailto

-0.60

 modelAndView

-0.60

Портал

-0.60

POSITIVE LOGITS

 listed

1.06

 listing

1.03

 listings

1.00

 lists

0.98

 Listed

0.94

listed

0.92

Listed

0.89

 list

0.89

 Listing

0.88

 Lists

0.86

Activations Density 0.312%

phrases that indicate items or elements being enumerated or specified

No Comments

No Known Activations