INDEX

Explanations

references to durations of time, particularly in weeks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 estimés

-0.75

यन

-0.60

Бахар

-0.58

StoreMessageInfo

-0.58

 nakalista

-0.57

/***/

-0.57

BeginInit

-0.57

 للاسماء

-0.54

complexContent

-0.54

POSITIVE LOGITS

 weeks

1.69

 month

1.57

weeks

1.45

 Weeks

1.41

 Month

1.39

 fortnight

1.37

Weeks

1.32

 WEEKS

1.29

 week

1.28

 MONTH

1.27

Activations Density 0.166%

references to durations of time, particularly in weeks

No Comments

No Known Activations