INDEX

Explanations

terms related to health and illness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 AssemblyCulture

-0.74

 nonatomic

-0.66

 Esco

-0.58

roek

-0.58

 خس

-0.55

olol

-0.54

weif

-0.54

 Atwood

-0.52

 Teng

-0.50

 Patro

-0.48

POSITIVE LOGITS

 diseases

0.99

 sick

0.99

 illnesses

0.98

sick

0.95

 illness

0.94

 disease

0.88

diseases

0.88

Sick

0.88

 sickness

0.86

 malade

0.83

Activations Density 0.308%

terms related to health and illness

No Comments

No Known Activations

terms related to health and illness

No Comments

No Known Activations