INDEX

Explanations

terms related to biology and bioinformatics

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

"bio" as a prefix

np_acts-logits-general · gemini-2.0-flash

prefix bio

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

WriteBarrier

-0.83

 وتسجيلات

-0.68

 participle

-0.68

})));

-0.66

Obrázky

-0.65

 correctes

-0.65

NullException

-0.64

########.

-0.64

HostException

-0.63

 typelib

-0.63

POSITIVE LOGITS

bio

1.20

Bio

1.09

Bio

0.93

bio

0.84

BIO

0.80

 био

0.73

 Bios

0.66

 bios

0.66

Bios

0.64

BIO

0.64

Activations Density 0.102%

terms related to biology and bioinformatics

"bio" as a prefix

prefix bio

No Comments

No Known Activations