INDEX

Explanations

terms related to medical or biological processes and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

InstanceState

-0.52

inetti

-0.52

 ISNI

-0.47

 Архів

-0.47

blica

-0.47

etCode

-0.46

adpleegd

-0.45

 pageable

-0.45

oor

-0.44

pied

-0.43

POSITIVE LOGITS

 development

2.77

development

2.41

 develop

2.36

 Development

2.24

Development

2.22

 développement

2.16

develop

2.16

 DEVELOPMENT

2.15

 develops

2.14

 developing

2.12

Activations Density 0.516%

terms related to medical or biological processes and their implications

No Comments

No Known Activations