INDEX

Explanations

elements related to programming syntax and structure

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

Code snippets and non-English text

np_acts-logits-general · gemini-2.0-flash

programming contexts and technical terms

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

ViewFeatures

-0.65

WriteBarrier

-0.56

 commerciali

-0.53

 beina

-0.52

"")

-0.52

 setuptools

-0.50

-0.49

 malades

-0.49

onAttach

-0.49

 Maggio

-0.48

POSITIVE LOGITS

 متعلقه

0.68

ReusableCell

0.59

 EconPapers

0.58

homonymie

0.58

ruptedException

0.57

 surla

0.55

PhysRev

0.54

 Wayback

0.52

PointerException

0.52

WaitGroup

0.52

Activations Density 0.064%

elements related to programming syntax and structure

Code snippets and non-English text

programming contexts and technical terms

No Comments

No Known Activations