INDEX

Explanations

phrases related to active participation or engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ViewChild

-0.45

 WebDriverWait

-0.44

 linkovi

-0.43

demment

-0.42

IBarButtonItem

-0.41

 Hathaway

-0.41

Gebruik

-0.40

 Asbury

-0.40

 Ruhm

-0.40

 besch

-0.39

POSITIVE LOGITS

 confirmed

0.75

 active

0.69

 Confirmed

0.64

confirmed

0.63

 verified

0.62

 disabled

0.56

 Verified

0.55

 actif

0.55

active

0.55

Disabled

0.55

Activations Density 0.193%

phrases related to active participation or engagement

No Comments

No Known Activations