INDEX

Explanations

the word "individual" and related professions.

oai_token-act-pair · gemini-2.0-flash

individual

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-1.70

-1.48

the

-1.47

-1.38

-1.37

↵

-1.27

-1.21

<eos>

-1.21

-1.20

POSITIVE LOGITS

Efq

2.94

 itſelf

2.92

 myſelf

2.91

 Theſe

2.89

 Jefus

2.86

 Majefty

2.77

 Monfieur

2.75

 purpoſe

2.67

 Houſe

2.64

 Anſ

2.63

Activations Density 2.840%

the word "individual" and related professions.

individual

No Comments

No Known Activations