INDEX

Explanations

references to drivers, particularly in contexts involving hardware and car operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

zoek

-0.65

ruptcy

-0.64

 parcourir

-0.64

 ویکی‌آمباردا

-0.64

UNC

-0.63

Naissance

-0.60

pago

-0.60

 Greenberg

-0.59

forRoot

-0.58

Cách

-0.58

POSITIVE LOGITS

 driver

2.32

 Driver

2.25

 Drivers

2.23

 drivers

2.23

driver

2.17

Driver

2.10

 DRIVER

2.10

Drivers

2.02

drivers

1.97

DRIVER

1.86

Activations Density 0.071%

references to drivers, particularly in contexts involving hardware and car operations

No Comments

No Known Activations