INDEX

Explanations

medical terminology related to conditions, specifically focusing on seizures and brain imaging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

IVEREF

-0.65

ThemeOverlay

-0.61

={{

-0.49

sơ

-0.48

 mechanism

-0.48

stup

-0.46

 Mechanism

-0.45

волю

-0.44

 Paterson

-0.43

lless

-0.43

POSITIVE LOGITS

Efq

0.86

 purpoſe

0.83

 myſelf

0.81

 uſe

0.78

 ſtate

0.78

 houſe

0.76

 deſt

0.76

 juſ

0.75

 juſt

0.75

 Jefus

0.74

Activations Density 0.954%

medical terminology related to conditions, specifically focusing on seizures and brain imaging

No Comments

No Known Activations