INDEX

Explanations

concepts related to health, medical conditions, and biological research

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

followed by "than," "whose," or prepositions

np_acts-logits-general · gemini-2.0-flash

specific nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

WebVitals

-0.74

Bibliograf

-0.73

,:,

-0.70

]")]

-0.68

twimg

-0.68

 OFDb

-0.65

āciju

-0.63

 समीक्षक

-0.63

esterday

-0.63

sizeCache

-0.63

POSITIVE LOGITS

 containing

1.04

 whose

0.87

 lacking

0.83

 without

0.81

 featuring

0.80

 ayant

0.78

 Containing

0.78

 contenant

0.76

ที่มี

0.75

 possessing

0.74

Activations Density 1.452%

concepts related to health, medical conditions, and biological research

followed by "than," "whose," or prepositions

specific nouns

No Comments

No Known Activations