INDEX

Explanations

phrases and terms related to health, medical outcomes, and studies involving patient data

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

Preceding words of "because" or similar

np_acts-logits-general · gemini-2.0-flash

because, due to

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

migrationBuilder

-1.03

interopRequire

-0.86

sizeCache

-0.81

DockStyle

-0.75

:✨

-0.75

 snippetHide

-0.74

rungsseite

-0.74

omitempty

-0.73

makeConstraints

-0.72

__*/

-0.69

POSITIVE LOGITS

 because

2.89

due

2.85

because

2.40

 debido

2.35

due

2.33

 devido

2.17

 BECAUSE

2.12

Because

2.08

 porque

2.06

 karena

2.04

Activations Density 1.209%

phrases and terms related to health, medical outcomes, and studies involving patient data

Preceding words of "because" or similar

because, due to

No Comments

No Known Activations