INDEX

Explanations

elements related to data processing and algorithms

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

adding or including something

np_acts-logits-general · gemini-2.0-flash

added, addition, including

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

findpost

-0.58

ViewFeatures

-0.58

SourceChecksum

-0.57

eleste

-0.55

SequentialGroup

-0.52

extAlignment

-0.51

endphp

-0.50

﴿

-0.50

 TextAlign

-0.49

XmlEnum

-0.47

POSITIVE LOGITS

 added

3.17

 adding

3.13

add

3.10

 addition

3.00

 Adding

2.97

Adding

2.88

 adds

2.85

 additions

2.83

added

2.76

 Added

2.76

Activations Density 1.178%

elements related to data processing and algorithms

adding or including something

added, addition, including

No Comments

No Known Activations