INDEX

Explanations

medical terminology and references to specific treatments or patient conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

GEBURTSDATUM

-1.06

 Theſe

-0.85

 ―――――

-0.75

 itſelf

-0.73

存于互联网档案馆

-0.72

 initComponents

-0.72

 whoſe

-0.70

ValueStyle

-0.68

>\<^

-0.66

jupiter

-0.66

POSITIVE LOGITS

Shi

0.64

Er

0.63

Shi

0.62

0.60

Le

0.60

Er

0.59

Ost

0.59

Hol

0.59

Le

0.59

Mal

0.59

Activations Density 1.745%

medical terminology and references to specific treatments or patient conditions

No Comments

No Known Activations