INDEX

Explanations

terms related to medical prescriptions and prescribed medications

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

djangoproject

-0.97

 resourceCulture

-0.96

 незавершена

-0.92

ThroughAttribute

-0.91

WebVitals

-0.90

annica

-0.89

extAlignment

-0.88

انجليز

-0.88

 kaynağından

-0.87

談社

-0.86

POSITIVE LOGITS

 prescription

1.37

 Prescription

1.30

 prescriptions

1.20

Prescription

1.19

 prescribe

1.18

prescription

1.16

Pres

1.03

Rx

1.02

 PRES

1.00

 prescribing

0.99

Activations Density 0.048%

terms related to medical prescriptions and prescribed medications

No Known Activations