INDEX

Explanations

names of people, particularly scientists, sometimes followed by institutional affiliations or project names.

oai_token-act-pair · gemini-2.0-flash

specific formatting or citation patterns

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

Citations

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

 Normdatei

-0.78

 vectorielles

-0.77

 refusé

-0.74

 africains

-0.73

bootstrapcdn

-0.71

 reele

-0.68

 comportements

-0.65

 militaires

-0.64

 humaines

-0.63

 supérieures

-0.63

POSITIVE LOGITS

}}</

0.50

Geografi

0.48

 useContext

0.47

iolo

0.46

#+#

0.46

gés

0.46

Edm

0.45

StoryboardSegue

0.44

GEBURTSDATUM

0.44

)</

0.43

Activations Density 0.491%

names of people, particularly scientists, sometimes followed by institutional affiliations or project names.

specific formatting or citation patterns

Citations

No Comments

No Known Activations