INDEX

Explanations

a variety of formatting markup, including certain HTML tags and list characters

oai_token-act-pair · gemini-2.0-flash

special characters or specific formatting

np_token-act-pair-logits · gpt-4o-mini

source code or markup

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-1.59

-1.32

-1.30

«

-1.29

-1.28

the

-1.27

-1.26

POSITIVE LOGITS

 itſelf

2.61

 Shakspeare

2.36

 myſelf

2.28

 Diſ

2.28

 Reſ

2.25

 ་་

2.25

 Anſ

2.25

 Monfieur

2.22

 Houſe

2.20

 Majefty

2.19

Activations Density 3.998%

a variety of formatting markup, including certain HTML tags and list characters

special characters or specific formatting

source code or markup

No Comments

No Known Activations