INDEX

Explanations

text related to machine learning datasets

oai_token-act-pair · gemini-2.0-flash

machine learning

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Werner

-0.53

::_('

-0.51

 Lock

-0.50

Cursors

-0.50

dealloc

-0.50

ThroughAttribute

-0.50

Werner

-0.50

 educativas

-0.49

LElement

-0.48

 cesse

-0.47

POSITIVE LOGITS

 machine

0.85

machine

0.75

 Machine

0.72

Machine

0.66

 Natural

0.64

 classification

0.63

 natural

0.62

Natural

0.60

 MACHINE

0.59

hyrchwyd

0.58

Activations Density 3.151%

text related to machine learning datasets

machine learning

No Comments

No Known Activations