INDEX

Explanations

terms and phrases associated with medical and biological analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

SequentialGroup

-0.89

 typelib

-0.72

phone

-0.71

 Phone

-0.69

Phone

-0.69

EndProject

-0.68

Teléfono

-0.68

MemoryWarning

-0.67

 phone

-0.66

 PHONE

-0.66

POSITIVE LOGITS

Fax

0.77

Fax

0.75

fax

0.71

FAX

0.62

 email

0.62

fax

0.60

Email

0.56

FAX

0.54

square

0.54

email

0.50

Activations Density 0.043%

terms and phrases associated with medical and biological analysis

No Comments

No Known Activations