INDEX

Explanations

references to riddles and questions related to them

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

asking questions and answers

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

It detects when the text is about puzzles, riddles, questions and their answers or discussion of solving them.

oai_token-act-pair · gpt-5-mini

Triggered by @vetterc0

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

bahnen

-0.36

TableAdapter

-0.34

 Liebe

-0.34

Kaynak

-0.34

Applet

-0.33

ulateur

-0.33

unitas

-0.32

 auxiliary

-0.32

Formik

-0.32

springen

-0.32

POSITIVE LOGITS

 Autorizaciones

0.52

 riddles

0.52

isContained

0.49

 disambiguazione

0.49

 يتيمه

0.49

 estekak

0.47

ldc

0.47

 ddelweddau

0.47

>{@

0.46

RTLD

0.46

Activations Density 0.417%

references to riddles and questions related to them

asking questions and answers

It detects when the text is about puzzles, riddles, questions and their answers or discussion of solving them.

No Known Activations