INDEX

Explanations

clinical terminology and numerical data related to medical studies

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

Abbreviations for US states

np_acts-logits-general · gemini-2.0-flash

US state abbreviations

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

Whilst

-1.01

 Whilst

-0.99

 whilst

-0.85

-0.83

 diatas

-0.81

 Amongst

-0.78

-0.75

‘

-0.73

の為

-0.72

 amongst

-0.72

POSITIVE LOGITS

—

0.91

”—

0.83

?—

0.83

)—

0.80

!—

0.79

—"

0.76

 Infór

0.76

—

0.74

Vidite

0.72

—,

0.71

Activations Density 1.655%

clinical terminology and numerical data related to medical studies

Abbreviations for US states

US state abbreviations

No Comments

No Known Activations