INDEX

Explanations

instances of the word "que" in various forms and contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 contextLoads

-1.17

 itſelf

-1.16

 Chriſt

-1.14

 auffi

-1.13

 iſt

-1.11

 Theſe

-1.09

Personendaten

-1.06

 Beſ

-1.05

ApplicationTests

-1.04

 purpoſe

-1.04

POSITIVE LOGITS

Que

1.27

Que

1.22

que

1.16

que

0.98

QUE

0.93

że

0.84

Qué

0.75

Qui

0.71

QUE

0.71

Qui

0.67

Activations Density 0.013%

instances of the word "que" in various forms and contexts

No Comments

No Known Activations