INDEX

Explanations

words relating to academic institutions and people affiliated with them

oai_token-act-pair · gemini-2.0-flash

technical or academic content

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

job titles and academia

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WebServlet

-0.73

parsedMessage

-0.63

transQ

-0.60

 nahilalakip

-0.60

featureID

-0.60

ArgumentParser

-0.59

Vidite

-0.58



-0.58

PropertyChanging

-0.57

 <>",

-0.57

POSITIVE LOGITS

})*/

0.61

سطس

0.59

 uncut

0.54

forhold

0.53

lectic

0.50

});*/

0.50

izier

0.49

MILLISECONDS

0.49

cinogen

0.48

UrlResolution

0.48

Activations Density 2.220%

words relating to academic institutions and people affiliated with them

technical or academic content

job titles and academia

No Comments

No Known Activations