INDEX

Explanations

elements related to mathematical or scientific notation and formatting

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

after common verbs

np_acts-logits-general · gemini-2.0-flash

had, was, tended

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

Билгалдахарш

-0.63

 Recuperado

-0.49

 hintergrund

-0.49

BufferException

-0.48

 podjela

-0.47

 vectorielle

-0.46

Kaynakça

-0.45

veien

-0.45

İstinadlar

-0.45

 abstrait

-0.45

POSITIVE LOGITS

+#+#

0.94

tagHelperRunner

0.84

省市镇

0.71

Autoritní

0.69

 дописавши

0.67

 bezeichneter

0.66

 تضيفلها

0.66

BeginContext

0.65

expandindo

0.65

ArgsConstructor

0.64

Activations Density 2.013%

elements related to mathematical or scientific notation and formatting

after common verbs

had, was, tended

No Comments

No Known Activations