INDEX

Explanations

variations of the word "or"

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

"or so" construction

np_acts-logits-general · gemini-2.0-flash

or so, or two, or less

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 препратки

-0.73

 Normdatei

-0.73

 للاسماء

-0.67

means

-0.67

webElementXpaths

-0.67

Према

-0.66

Means

-0.65

 AssemblyCulture

-0.64

LookAnd

-0.63

expandindo

-0.61

POSITIVE LOGITS

 ther

0.81

 POSS

0.68

 sooner

0.64

 longer

0.64

 giù

0.62

so

0.58

 less

0.57

ătate

0.57

 beyond

0.57

 older

0.56

Activations Density 0.127%

variations of the word "or"

"or so" construction

or so, or two, or less

No Comments

No Known Activations