INDEX

Explanations

references to official documentation or licenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

mybatisplus

-0.65

 snippetHide

-0.59

hésite

-0.58

 laikā

-0.53

 RequestMethod

-0.52

zupeł

-0.52

annica

-0.52

Résultats

-0.51

formik

-0.51

reactivex

-0.51

POSITIVE LOGITS

 Copyright

0.97

Copyright

0.91

©

0.79

Created

0.78

created

0.75

©

0.75

 Created

0.74

 copyright

0.73

 created

0.73

Date

0.69

Activations Density 0.297%

references to official documentation or licenses

No Comments

No Known Activations