INDEX

Explanations

words related to computing, automation, and analysis.

oai_token-act-pair · gemini-2.0-flash

artificial intelligence and automation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

PreExecute

-0.65

}],

-0.59

+#+

-0.58



-0.58

 bezeichneter

-0.54

]")]

-0.54

phas

-0.51

 useStyles

-0.51

::::::::

-0.51

endsection

-0.50

POSITIVE LOGITS

 automat

0.68

 automatically

0.68

 automatic

0.65

 Automat

0.63

 Automatic

0.62

 onOptions

0.60

 automated

0.60

 автоматически

0.60

 automatiquement

0.60

automated

0.59

Activations Density 1.189%

words related to computing, automation, and analysis.

artificial intelligence and automation

No Comments

No Known Activations