INDEX

Explanations

structured data, particularly mathematical or programming syntax

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntentFilter

-0.48

Advertisements

-0.47

 borer

-0.47

 Kleid

-0.45

yntaxException

-0.44

ogaster

-0.44

Quoting

-0.44

USI

-0.44

 studying

-0.43

 שוליים

-0.42

POSITIVE LOGITS

AnchorStyles

0.67

 BoxFit

0.63

 kasarigan

0.63

msgTypes

0.59

livan

0.58

rededor

0.58

 aDecoder

0.57

setViewportView

0.56

出版年

0.55

gridad

0.55

Activations Density 0.341%

structured data, particularly mathematical or programming syntax

No Comments

No Known Activations