INDEX

Explanations

professional qualifications and certifications

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

잃

-0.43

 invari

-0.42

DebuggerNonUser

-0.42

 Plea

-0.41

XtraReports

-0.41

 Newsroom

-0.40

лися

-0.39

dô

-0.39

 Bete

-0.39

кли

-0.39

POSITIVE LOGITS

 Certified

1.07

Certified

0.98

 certified

0.91

InjectMocks

0.78

certified

0.78

 certification

0.75

 certifications

0.74

Efq

0.73

 NSCoder

0.71

Dip

0.71

Activations Density 0.096%

professional qualifications and certifications

No Comments

No Known Activations