INDEX

Explanations

technical terms and code structures related to programming and data processing

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

Characters commonly used in code

np_acts-logits-general · gemini-2.0-flash

function parameter lists

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

зер

-0.50

LoggerFactory

-0.46

 никто

-0.44

jście

-0.43

 här

-0.42

 world

-0.42

 тран

-0.42

let

-0.41

 UIButton

-0.41

as

-0.40

POSITIVE LOGITS

expandindo

0.93

:✨

0.90

 kaarangay

0.88

 AssemblyCompany

0.87

Personensuche

0.86

 ProtoMessage

0.86

 nahilalakip

0.85

 الحره

0.81

Portály

0.78

InjectAttribute

0.78

Activations Density 0.566%

technical terms and code structures related to programming and data processing

Characters commonly used in code

function parameter lists

No Comments

No Known Activations