INDEX

Explanations

coding constructs related to function definitions and parameters

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

Code, references, or math syntax

np_acts-logits-general · gemini-2.0-flash

Python type hints, function signatures

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

DoubleQuotes

-0.69

oa̍t

-0.69

GOTREF

-0.64

LogFactory

-0.62

таратура

-0.59

енча

-0.58

endphp

-0.57

borderSide

-0.57

HostException

-0.56

XmlType

-0.56

POSITIVE LOGITS

str

0.70

str

0.69

intios

0.60

 للاسماء

0.59

 الرياضيه

0.53

Personensuche

0.52

Union

0.51

 Union

0.50

WebVitals

0.48

Str

0.47

Activations Density 0.496%

coding constructs related to function definitions and parameters

Code, references, or math syntax

Python type hints, function signatures

No Comments

No Known Activations