INDEX

Explanations

words related to healthcare paired with words of action such as 'use' or 'develop.'

oai_token-act-pair · gemini-2.0-flash

customers/patients

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

 estekak

-0.97

 ProtoMessage

-0.87

UnsafeEnabled

-0.82

 resourceCulture

-0.77

")));

-0.75

 externi

-0.75

IVEREF

-0.74

SharedDtor

-0.73

"]];

-0.73

 muualla

-0.69

POSITIVE LOGITS

 patients

1.32

 patient

1.16

 clients

1.13

 customers

1.09

 Patients

1.09

 client

0.99

Patients

0.99

 passengers

0.96

 Clients

0.94

 Patient

0.88

Activations Density 3.273%

words related to healthcare paired with words of action such as 'use' or 'develop.'

customers/patients

No Comments

No Known Activations