INDEX

Explanations

code-related terminology

oai_token-act-pair · gemini-2.0-flash

tips and tricks

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

 nahilalakip

-0.68

PhysRevD

-0.57

GEBURTSDATUM

-0.57

 ModelExpression

-0.56

AttributeSet

-0.56

 FetchType

-0.55

complexContent

-0.54

webElementXpaths

-0.52

 defaultstate

-0.50

XMLSchema

-0.50

POSITIVE LOGITS

 trick

1.31

 hack

1.28

 hacks

1.15

trick

1.15

 Trick

1.14

 HACK

1.12

 tricks

1.10

hack

1.09

 Tricks

1.03

Trick

0.96

Activations Density 1.379%

code-related terminology

tips and tricks

No Comments

No Known Activations