INDEX

Explanations

references to various entities, particularly in the context of medical and biological subjects

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 sẻ

-0.48

vábbi

-0.42

 elog

-0.42

ęb

-0.39

кали

-0.39

 ander

-0.37

 possibile

-0.37

 colspan

-0.36

توض

-0.36

 fine

-0.36

POSITIVE LOGITS

modelBuilder

0.87

 незавершена

0.79

 Italijanski

0.78

AutoField

0.76

__(/*!

0.75

errHandler

0.75

GEBURTSDATUM

0.74

UVWXYZ

0.74

 AssemblyCompany

0.72

bootstrapcdn

0.72

Activations Density 0.426%

references to various entities, particularly in the context of medical and biological subjects

No Comments

No Known Activations