INDEX

Explanations

technical terms and code-related syntax

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

Code-related terms and operations

np_acts-logits-general · gemini-2.0-flash

I/O completion status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

adaptiveStyles

-0.60

tvguidetime

-0.54

szer

-0.47

 nahilalakip

-0.46

 kasarigan

-0.46

XmlAccessorType

-0.46

ATIC

-0.44

XmlAttribute

-0.43

="@+

-0.43

AppCompat

-0.42

POSITIVE LOGITS

 read

0.83

 write

0.76

 waiting

0.74

 buffer

0.73

 Write

0.73

 transfer

0.72

 Read

0.72

 reads

0.72

 writes

0.70

 completion

0.70

Activations Density 0.800%

technical terms and code-related syntax

Code-related terms and operations

I/O completion status

No Comments

No Known Activations