INDEX

Explanations

references to weeks and time periods within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ISI

-0.70

cshtml

-0.69

 Salisbury

-0.67

umman

-0.65

$_['

-0.64

isbury

-0.64

 Kombat

-0.64

 pstmt

-0.62

ousine

-0.60

 للاسماء

-0.59

POSITIVE LOGITS

 week

1.70

 weeks

1.70

 Weeks

1.69

 WEEK

1.68

 Week

1.60

weeks

1.58

WEEK

1.55

 WEEKS

1.54

week

1.53

Week

1.51

Activations Density 0.104%

references to weeks and time periods within a document

No Comments

No Known Activations