INDEX

Explanations

the prefix "pre-" modifying a variety of nouns

oai_token-act-pair · gemini-2.0-flash

pre

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

pre

-2.89

Pre

-2.48

Pre

-2.47

pre

-2.45

 pré

-1.91

PRE

-1.91

PRE

-1.85

预

-1.54

Pré

-1.37

pré

-1.36

POSITIVE LOGITS

 Wikimedijinoj

0.56

曖昧さ回避

0.53

astéroïdes

0.53

 podes

0.52

kuuta

0.52

 Wraith

0.51

 trast

0.50

 Programmer

0.50

 pouss

0.50

 Temporary

0.50

Activations Density 11.876%

the prefix "pre-" modifying a variety of nouns

pre

No Comments

No Known Activations