INDEX

Explanations

mentions of sicknesses and their symptoms, especially in relation to percentages and probability.

oai_token-act-pair · gemini-2.0-flash

medical symptoms

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArgsConstructor

-0.82

 purpoſe

-0.81

 faſt

-0.80

 pleaſure

-0.78

 ſmall

-0.78

 houſe

-0.75

 propOrder

-0.73

 Monfieur

-0.72

 AttributeSet

-0.72

 Jefus

-0.72

POSITIVE LOGITS

msgSender

0.50

 кӀ

0.41

Искәрмәләр

0.39

 sumpay

0.38

sitis

0.37

的身

0.37

Jar

0.36

InvalidProtocol

0.36

 câncer

0.35

 مشين

0.35

Activations Density 4.881%

mentions of sicknesses and their symptoms, especially in relation to percentages and probability.

medical symptoms

No Comments

No Known Activations