INDEX

Explanations

terms related to molecular biology and mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SuppressMessage

-0.98

 réforme

-0.88

 InputDecoration

-0.86

usitis

-0.83

 Whigs

-0.81

 nakalista

-0.79

SATA

-0.79

 Borja

-0.79

lidae

-0.77

 sidan

-0.77

POSITIVE LOGITS

 molecular

1.25

molecular

1.20

 Molecular

1.11

 molecules

1.09

Molecular

0.98

Mol

0.98

 Molecules

0.95

 Mole

0.93

lecular

0.89

 مول

0.88

Activations Density 0.018%

terms related to molecular biology and mechanisms

No Comments

No Known Activations