INDEX

Explanations

instances of the word "wear" and its variations in different contexts

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

midler

-0.45

équipement

-0.40

 verstär

-0.39

inghouse

-0.39

 σο

-0.37

 cozinha

-0.37

émission

-0.36

 Pani

-0.36

diali

-0.35

DeviceInfo

-0.35

POSITIVE LOGITS

 للمعارف

0.63

 ſta

0.57

//$

0.56

findpost

0.55

Alike

0.54

setArguments

0.54

 WEAR

0.53

Wear

0.53

 witness

0.52

 enterprise

0.52

Activations Density 0.342%

instances of the word "wear" and its variations in different contexts

No Comments

No Known Activations