INDEX

Explanations

mathematical conditions and logical constructs related to sets

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

Symbols, math, or code snippets

np_acts-logits-general · gemini-2.0-flash

each or foreach or dozen

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

protoimpl

-0.65

webElementXpaths

-0.63

 kasarigan

-0.62

PositiveButton

-0.57

InjectAttribute

-0.57

 joaat

-0.54

Tembelea

-0.54

ніципалі

-0.52

 isComment

-0.52

IonicModule

-0.50

POSITIVE LOGITS

一个个

0.99

 each

0.99

each

0.84

Each

0.84

 Each

0.84

 dozen

0.81

foreach

0.81

dozen

0.77

ForEach

0.76

 mỗi

0.75

Activations Density 1.377%

mathematical conditions and logical constructs related to sets

Symbols, math, or code snippets

each or foreach or dozen

No Comments

No Known Activations