INDEX

Explanations

terms related to drivers and driver-related programming concepts

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

software driver or program

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

fal

-0.31

 envoyé

-0.28

龇

-0.27

 gospod

-0.26

percentage

-0.25

dav

-0.25

Ener

-0.24

 jeunes

-0.24

CMAKE

-0.24

 ahor

-0.24

POSITIVE LOGITS

Driver

3.19

 Driver

2.94

 driver

2.48

driver

2.44

 DRIVER

2.38

 Drivers

2.22

DRIVER

2.20

Drivers

2.03

 drivers

2.00

getDriver

1.89

Activations Density 0.006%

terms related to drivers and driver-related programming concepts

software driver or program

No Comments

No Known Activations