INDEX

Explanations

numerical data and references

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

Citations with year

np_acts-logits-general · gemini-2.0-flash

academic citations

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

 radioactivity

-0.49

 séjours

-0.46

 født

-0.46

?>"

-0.45

Integral

-0.45

hoku

-0.44

 العزيز

-0.43

 Holliday

-0.43

 cartões

-0.43

HttpPost

-0.43

POSITIVE LOGITS

:✨

0.70

yntaxException

0.65

зулта

0.62

webElementXpaths

0.62

InjectMocks

0.61

WebVitals

0.61

ollectionView

0.61

 SEDS

0.60

 createContext

0.59

طلحات

0.58

Activations Density 0.362%

numerical data and references

Citations with year

academic citations

No Comments

No Known Activations