INDEX

Explanations

components related to programming constructs, particularly data structures and type definitions

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

after "size" or relating to size

np_acts-logits-general · gemini-2.0-flash

size_t values

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

InitVars

-0.79

 GeoNames

-0.74

createStatement

-0.69

 noDo

-0.68

verifyException

-0.68

parsedMessage

-0.67

Personensuche

-0.60

 eventdata

-0.59

contentLoaded

-0.57

はじめに

-0.56

POSITIVE LOGITS

BeginContext

0.62

0.56

0.53

 AppCompatTheme

0.52

cti

0.49

int

0.49

0.48

Type

0.48

type

0.48

 itemprop

0.46

Activations Density 0.162%

components related to programming constructs, particularly data structures and type definitions

after "size" or relating to size

size_t values

No Comments

No Known Activations