INDEX

Explanations

phrases involving questions and answers

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

strong language

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

discourse scaffolding and emphasis markers in informal text—negations, conjunctions, pronouns, quoted Q&A, repetitions, and list/quantity phrasing that signal conversational tone and intensity.

oai_token-act-pair · gpt-5 Triggered by @vetterc0

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 recognized

-0.37

 recognised

-0.35

 sejumlah

-0.33

griffe

-0.32

 voeten

-0.32

 ristor

-0.30

 sava

-0.30

 ancha

-0.29

 spirituale

-0.29

 reconocido

-0.29

POSITIVE LOGITS

GEBURTSDATUM

0.79

 oprot

0.75

rungsseite

0.71

 betweenstory

0.71

 autorytatywna

0.69

fuck

0.68

IntoConstraints

0.67

fucking

0.67

 goddamn

0.67

 fuckin

0.66

Activations Density 0.121%

phrases involving questions and answers

strong language

discourse scaffolding and emphasis markers in informal text—negations, conjunctions, pronouns, quoted Q&A, repetitions, and list/quantity phrasing that signal conversational tone and intensity.

No Comments

No Known Activations