INDEX

Explanations

instances of the word "this" and its variations

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

"this" introducing section or document

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

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

SharedCtor

-1.13

Personendaten

-1.02

 autorytatywna

-0.96

 linkovi

-0.95

 utafitiHapana

-0.93

 gynhyrchwyd

-0.89

Personensuche

-0.84

IntoConstraints

-0.84

GEBURTSDATUM

-0.82

Datuak

-0.81

POSITIVE LOGITS

 brief

0.51

 report

0.51

 chapter

0.49

 article

0.45

 document

0.44

 study

0.43

 guide

0.43

 Chapter

0.42

 program

0.42

 section

0.40

Activations Density 0.053%

instances of the word "this" and its variations

"this" introducing section or document

No Comments

No Known Activations