INDEX

Explanations

technical terms and jargon related to health and medical studies

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

Follows the letter "H"

np_acts-logits-general · gemini-2.0-flash

H followed by HPatches, HFD, H2O, Hibiscus, Heim, density

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 historical

-0.73

Historical

-0.70

historical

-0.64

horizontal

-0.56

 historic

-0.55

rouvez

-0.52

handling

-0.52

 horizontal

-0.51

 highlight

-0.51

 heritage

-0.51

POSITIVE LOGITS

 pylori

0.65

AutoField

0.60

PRWEB

0.59

bootstrapcdn

0.57

 sapiens

0.56

IntoConstraints

0.54

 Signalez

0.54

SourceChecksum

0.53

AppCompat

0.52

actylus

0.52

Activations Density 0.783%

technical terms and jargon related to health and medical studies

Follows the letter "H"

H followed by HPatches, HFD, H2O, Hibiscus, Heim, density

No Comments

No Known Activations