INDEX

Explanations

terms related to scientific publications and socioeconomic status

oai_token-act-pair · gemini-2.0-flash

scientific research

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 <=",

-1.09

SequentialGroup

-0.84

GEBURTSDATUM

-0.80

 Baillargeon

-0.79

<bos>

-0.79

 Roskov

-0.78

 يتيمه

-0.77

Vidite

-0.75

 nakalista

-0.71

 CreateTagHelper

-0.69

POSITIVE LOGITS

 sentenza

0.45

touch

0.42

 profondo

0.39

 profonda

0.39

kazu

0.37

 naught

0.37

示

0.37

Discuss

0.37

 subjective

0.35

Author

0.35

Activations Density 10.068%

terms related to scientific publications and socioeconomic status

scientific research

No Comments

No Known Activations