INDEX

Explanations

statistical terms and average metrics related to data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

WithIOException

-0.53

sedown

-0.48

matous

-0.48

ftagPool

-0.47

 faſt

-0.47

makeConstraints

-0.47

 informée

-0.46

erapeutic

-0.46

kuuta

-0.45

principalColumn

-0.45

POSITIVE LOGITS

 average

1.06

 Average

0.94

平均

0.92

Average

0.92

average

0.90

 averaging

0.80

 averages

0.79

 averaged

0.78

 AVERAGE

0.76

 mean

0.74

Activations Density 0.661%

statistical terms and average metrics related to data analysis

No Comments

No Known Activations