INDEX

Explanations

statements questioning or challenging political authority or norms.

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

mentions of political and governmental activities.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

dates and years, particularly recent years like 2016 and 2017.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Punctuation at the end of a sentence

np_acts-logits-general · gemini-2.0-flash

American politics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

XmlRootElement

-0.74

 للمعارف

-0.64

findpost

-0.61

SharedCtor

-0.59

UrlResolution

-0.58

庁

-0.56

Mrs

-0.54

//~

-0.53

SourceChecksum

-0.52

CopyWith

-0.52

POSITIVE LOGITS

extAlignment

0.61

 👇

0.59

 😅

0.57

 🙏

0.56

CNN

0.55

},[])

0.55

 💜

0.53

 tiktok

0.52

 POLIT

0.52

 }}"></

0.52

Activations Density 0.055%

statements questioning or challenging political authority or norms.

mentions of political and governmental activities.

dates and years, particularly recent years like 2016 and 2017.

Punctuation at the end of a sentence

American politics

No Comments

No Known Activations