INDEX

Explanations

references to specific scientific terms and entities, particularly in the context of medical research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

phins

-0.67

kegaard

-0.66

EqualsAnd

-0.66

ي

-0.64

"?>

-0.63

kx

-0.61

 Quij

-0.61

work

-0.61

 Nabi

-0.61

pidou

-0.61

POSITIVE LOGITS

MAR

1.54

 Martel

1.41

 Marr

1.38

Mar

1.36

Mar

1.33

MAR

1.32

 Marston

1.28

 Maru

1.27

 Marlowe

1.25

 marts

1.24

Activations Density 0.088%

references to specific scientific terms and entities, particularly in the context of medical research

No Comments

No Known Activations