INDEX

Explanations

references to specific biological terms, particularly related to immune system cells and their environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Moriarty

-0.67

Diction

-0.63

 Cheshire

-0.62

 Sirius

-0.62

Lü

-0.62

 Seif

-0.61

ly

-0.61

lic

-0.59

к

-0.59

 Garcia

-0.59

POSITIVE LOGITS

ValueStyle

1.15

 &___

1.09

AndroidJUnit

1.06

aarrggbb

1.05

 NSCoder

0.99

 SafeMath

0.97

Clik

0.95

NameInMap

0.95

oporosis

0.94

ImageContext

0.93

Activations Density 1.452%

references to specific biological terms, particularly related to immune system cells and their environments

No Comments

No Known Activations