INDEX

Explanations

block delimiters or structure indicators in code

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

code structure elements

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

最快更新

-0.55

Jîn

-0.53

 inoxydable

-0.53

pozycji

-0.53

vocations

-0.51

-0.49

 continúas

-0.49

cshtml

-0.48

chomp

-0.47

and

-0.46

POSITIVE LOGITS

ьаж

0.98

RegistryLite

0.71

تقاوى

0.71

 kasarigan

0.69

 utafitiHapana

0.68

ngdoc

0.67

 contextLoads

0.67

 tartalomajánló

0.65

 cherchés

0.63

Activations Density 0.033%

block delimiters or structure indicators in code

code structure elements

No Comments

No Known Activations