INDEX

Explanations

the word "Or" in various contexts and formats

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

Follows "Or" or "OR"

np_acts-logits-general · gemini-2.0-flash

Or and words starting with Or

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

intios

-0.85

{}{}

-0.85

참고

-0.76

 Normdatei

-0.74

 iVar

-0.74

DoubleQuotes

-0.70

utives

-0.69

sidemargin

-0.69

mybatisplus

-0.68

 незавершена

-0.68

POSITIVE LOGITS

 else

0.51

Or

0.51

else

0.51

 equivalently

0.49

 giù

0.48

 rather

0.47

 alternatively

0.47

 seja

0.47

OR

0.45

textTheme

0.43

Activations Density 0.150%

the word "Or" in various contexts and formats

Follows "Or" or "OR"

Or and words starting with Or

No Comments

No Known Activations