INDEX

Explanations

technical terms related to CPU identification and management

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

after "Intel", "HP", or "Lenovo"

np_acts-logits-general · gemini-2.0-flash

computer hardware and components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

migrationBuilder

-0.53

 Lucas

-0.48

 svě

-0.45

Lucas

-0.45

 Butterworth

-0.44

клопе

-0.44

 scio

-0.43

법

-0.42

tifical

-0.41

Binance

-0.41

POSITIVE LOGITS

ImageContext

0.69

 Intel

0.66

 BIOS

0.65

✨:

0.62

 informée

0.61

 kiến

0.60

 mother

0.60

intel

0.59

 Bios

0.59

__":

0.58

Activations Density 0.450%

technical terms related to CPU identification and management

after "Intel", "HP", or "Lenovo"

computer hardware and components

No Comments

No Known Activations