INDEX

Explanations

boolean values and logical assertions

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

boolean values and their state (true or false)

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

introduces specific entities

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

fromnode

-0.93

RegressionTest

-0.87

cshtml

-0.80

ItemBackground

-0.75

SharedCtor

-0.68

 Италијани

-0.65

tonsoft

-0.64

########.

-0.62

>{@

-0.62

IUrlHelper

-0.61

POSITIVE LOGITS

 True

0.53

 False

0.47

 CURIAM

0.46

True

0.46

 true

0.46

uwen

0.45

TRUE

0.45

FALSE

0.45

 mendatang

0.44

 esterni

0.43

Activations Density 0.029%

boolean values and logical assertions

boolean values and their state (true or false)

introduces specific entities

No Comments

No Known Activations