INDEX

Explanations

words and phrases that indicate someone is being discouraged or prevented from doing something

oai_token-act-pair · gemini-2.0-flash

discouragement/prevention

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

)}_{

-0.59

 PeEnEo

-0.59

IsMutable

-0.56

.")]

-0.52

})_{

-0.52

resizingMask

-0.52

}}/>

-0.51

 Millard

-0.50

}}_{

-0.50

>>()

-0.48

POSITIVE LOGITS

autique

0.56

ArgumentParser

0.54

تقاوى

0.52

 leading

0.50

igate

0.50

Демографія

0.50

 flow

0.49

 fieldNum

0.47

leading

0.47

DebuggerNonUser

0.47

Activations Density 2.855%

words and phrases that indicate someone is being discouraged or prevented from doing something

discouragement/prevention

No Comments

No Known Activations