INDEX

Explanations

words and phrases that indicate taking immediate action

oai_token-act-pair · gemini-2.0-flash

act now/soon

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

before

-0.97

 before

-0.96

 Before

-0.94

Before

-0.86

 antes

-0.84

 BEFORE

-0.83

 sebelum

-0.82

MessageOf

-0.81

 bevor

-0.81

BEFORE

-0.80

POSITIVE LOGITS

escens

0.45

$_['

0.43

 ژان

0.43

ggere

0.43

 streak

0.39

HideFlags

0.38

ungsver

0.37

RemoveField

0.37

Euler

0.37

 ladri

0.37

Activations Density 1.046%

words and phrases that indicate taking immediate action

act now/soon

No Comments

No Known Activations