INDEX

Explanations

instances of 'thought' or a synonym for it

oai_token-act-pair · gemini-2.0-flash

thought

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

oyn

-0.42

 sondern

-0.41

 Amiens

-0.40

Ārējās

-0.40

RefNanny

-0.40

orkin

-0.39

 pout

-0.38

 decre

-0.38

Abr

-0.38

avadoc

-0.38

POSITIVE LOGITS

RectangleBorder

0.86



0.76

 jScrollPane

0.73

contentLoaded

0.69

migrationBuilder

0.68

ValueStyle

0.66

adaptiveStyles

0.66

SerializedSize

0.66

 that

0.63

 sessionFactory

0.62

Activations Density 0.700%

instances of 'thought' or a synonym for it

thought

No Comments

No Known Activations