INDEX

Explanations

punctuated phrases and statements

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

Sentences ending with a period

np_acts-logits-general · gemini-2.0-flash

end of sentence or clause

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

The period mark (.) is a punctuation marker that typically appears at the end of independent clauses or complete sentences, functioning as a sentence boundary indicator in academic and literary text.

eleuther_acts_top20 · claude-4-5-haiku Triggered by @kparkhamchuk

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

 myſelf

-0.90

 Majefty

-0.86

 himſelf

-0.85

 ſeveral

-0.85

 themſelves

-0.84

 تانيه

-0.83

 purpoſe

-0.81

yntaxException

-0.81

 iſt

-0.79

 Anſ

-0.79

POSITIVE LOGITS

 Whereas

0.68

Whereas

0.68

 Thus

0.65

Thus

0.63

Indeed

0.62

 Indeed

0.59

 “[

0.58

Viewed