INDEX

Explanations

markers or indicators of the beginning of a new section or paragraph

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

instances of the document structure's beginning

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

numbers and math symbols

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enschappe

-0.63

 TestBed

-0.61

zog

-0.57

しまいました

-0.57

ParallelGroup

-0.56

 Phipps

-0.55

một

-0.52

 Assistance

-0.52

orial

-0.52

rail

-0.51

POSITIVE LOGITS

APORE

0.77

 الحره

0.69

 Moslem

0.65

*/].

0.64

GEBURTSDATUM

0.63

 BorderRadius

0.62

istoitu

0.62

Filmographie

0.61

RectangleBorder

0.60

DockStyle

0.59

Activations Density 0.001%

markers or indicators of the beginning of a new section or paragraph

instances of the document structure's beginning

numbers and math symbols

No Comments

No Known Activations