INDEX

Explanations

terms related to medical care and primary healthcare providers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 TableColumn

-0.52

 Table

-0.52

</table>

-0.52

 cake

-0.50

 pestaña

-0.49

 pernas

-0.47

Fig

-0.47

fusc

-0.47

 balon

-0.47

 tela

-0.47

POSITIVE LOGITS

 Primary

0.76

 primary

0.76

 PRIMARY

0.75

Primary

0.70

 kasarigan

0.67

 primacy

0.64

 priority

0.64

primary

0.63

PRIMARY

0.63

 prime

0.63

Activations Density 0.194%

terms related to medical care and primary healthcare providers

No Comments

No Known Activations