INDEX

Explanations

references to logging mechanisms and their configurations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ISupport

-0.48

hingga

-0.47

、《

-0.45

honneur

-0.43

 Pape

-0.42

 landet

-0.42

 żyw

-0.42

χρι

-0.41

runOnUiThread

-0.40

 estou

-0.40

POSITIVE LOGITS

jspx

1.63

Logger

1.48

 Logger

1.36

 defaultstate

1.16

addPreferredGap

1.07

ContentAsync

1.00

UnknownFields

0.95

 nahilalakip

0.95

matchCondition

0.93

getLogger

0.91

Activations Density 0.013%

references to logging mechanisms and their configurations in code

No Comments

No Known Activations