INDEX

Explanations

word fragments starting with "bel"

oai_token-act-pair · gemini-2.0-flash

Bel/Bell

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.79

omitempty

-0.67

NewUrlParser

-0.63

XmlAccessType

-0.62

 désolés

-0.61

PhysRevD

-0.61

ioutil

-0.59

각주

-0.58

 références

-0.56

POSITIVE LOGITS

isle

0.55

 />);

0.51

saraba

0.48

 olev

0.47

on

0.46

gua

0.45

tran

0.45

 заме

0.43

idavit

0.43

monte

0.43

Activations Density 0.355%

word fragments starting with "bel"

Bel/Bell

No Comments

No Known Activations