INDEX

Explanations

words related to inspiration

oai_token-act-pair · gemini-2.0-flash

inspire

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

httphttps

-0.81

исленность

-0.73

 Mahabhar

-0.62

 pinulongan

-0.62

fony

-0.60

 mohair

-0.60

Portale

-0.60

xious

-0.59

 sheen

-0.59

INSEE

-0.57

POSITIVE LOGITS

Meth

0.50

 felicità

0.47

 OMITBAD

0.46

 semplici

0.45

me

0.43

 oreilles

0.43

to

0.42

ReusableCell

0.42

 meth

0.41

atzung

0.40

Activations Density 2.034%

words related to inspiration

inspire

No Comments

No Known Activations