INDEX

Explanations

terminology related to bioinformatics and biological research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 correctes

-0.70

rrggbb

-0.69

 nakalista

-0.65

 FetchType

-0.64

WriteBarrier

-0.63

StructEnd

-0.62

 MainAxisSize

-0.61

 shaker

-0.61

✨:

-0.61

########.

-0.60

POSITIVE LOGITS

bio

1.13

Bio

1.01

Bio

0.83

bio

0.70

BIO

0.70

 био

0.68

 bios

0.62

 生物

0.53

 biome

0.52

 Bios

0.49

Activations Density 0.075%

terminology related to bioinformatics and biological research

No Comments

No Known Activations