INDEX

Explanations

theoretical concepts and detailed information related to statistics and measurement in various contexts

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

--){

-0.52

nodoc

-0.52

 clock

-0.49

/^

-0.49

 leggen

-0.48

essy

-0.48

ั่ง

-0.48

webElementXpaths

-0.48

gorm

-0.47

ymce

-0.46

POSITIVE LOGITS

 בלב

0.58

 saja

0.56

 sahaja

0.54

 thôi

0.53

AndEndTag

0.53

しか

0.51

Really

0.49

 väli

0.49

 Maximal

0.48

 Superhosts

0.46

Activations Density 0.762%

theoretical concepts and detailed information related to statistics and measurement in various contexts

No Comments

No Known Activations