INDEX

Explanations

references to specific scientific terms and entities related to genetics and pharmacology

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

談社

-0.59

</s>

-0.58

jamientos

-0.58

ActionCreators

-0.56

mstyle

-0.53

أ

-0.53

mtd

-0.51

expandindo

-0.51

 Chom

-0.51

PRNewswire

-0.50

POSITIVE LOGITS

VIAF

1.43

 Vance

1.36

VH

1.29

VH

1.26

getV

1.24

 VIAF

1.24

 Vaughn

1.21

VN

1.21

VF

1.21

 VEGF

1.17

Activations Density 1.461%

references to specific scientific terms and entities related to genetics and pharmacology

No Comments

No Known Activations