INDEX

Explanations

explanatory content and advice related to technical processes and tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 arşivlendi

-0.54

 betweenstory

-0.53

EndInit

-0.50

yntaxException

-0.50

\{\\

-0.50

 defaultstate

-0.48

makeText

-0.47

ThroughAttribute

-0.46

FormState

-0.43

endforeach

-0.43

POSITIVE LOGITS

you

0.52

 usually

0.49

 your

0.46

 Usually

0.45

 IIRC

0.44

 yourself

0.43

Usually

0.42

GEBURTSDATUM

0.42

 Wire

0.40

 informée

0.40

Activations Density 0.732%

explanatory content and advice related to technical processes and tools

No Comments

No Known Activations