INDEX

Explanations

terms related to biological entities, particularly focusing on microorganisms and infections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

StatusBar

-0.53

 Piel

-0.51

KURZBESCHREIBUNG

-0.49

 tartalomajánló

-0.49

 незавершена

-0.48

oflu

-0.47

Tikang

-0.47

 arşivlendi

-0.47

 regrettable

-0.46

 Dorothea

-0.46

POSITIVE LOGITS

Bug

0.86

 insect

0.86

 worm

0.85

 insects

0.83

 Insects

0.81

 Insect

0.81

 Worm

0.81

 Worms

0.78

 worms

0.77

URLException

0.75

Activations Density 2.421%

terms related to biological entities, particularly focusing on microorganisms and infections

No Comments

No Known Activations