INDEX

Explanations

uses of indefinite articles following verbs or prepositions and preceding a noun

oai_token-act-pair · gemini-2.0-flash

references to moments

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

a

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

expandindo

-0.77

AndroidJUnit

-0.70

évaluateur

-0.66

AsUp

-0.66

 InputDecoration

-0.66

 dimaksud

-0.65

 Roskov

-0.65

 '\\;'

-0.64

лтемелер

-0.62

Xaml

-0.61

POSITIVE LOGITS

GOTREF

0.52

 moment

0.50

 kiss

0.50

 sliver

0.47

AutoScale

0.45

Moment

0.45

 cheque

0.44

rdoba

0.43

 shout

0.43

moment

0.43

Activations Density 1.907%

uses of indefinite articles following verbs or prepositions and preceding a noun

references to moments

a

No Comments

No Known Activations