INDEX

Explanations

instances of dialogue or spoken expressions in the text

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

DeleteBehavior

-0.66

"]];

-0.65

complexType

-0.62

ViewImports

-0.60

complexContent

-0.59

__*/

-0.57

"])

-0.56

setViewportView

-0.55

 дописавши

-0.55

menea

-0.55

POSITIVE LOGITS

newArrayList

0.71

 tartalomajánló

0.67

 étoit

0.63

 avoient

0.63

 Majefty

0.62

 étoient

0.61

 Monfieur

0.59

 createState

0.59

Efq

0.58

 quæ

0.57

Activations Density 0.524%

instances of dialogue or spoken expressions in the text

No Comments

No Known Activations