INDEX

Explanations

words that imply permanence or eternity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

сылкі

-0.70

latego

-0.68

RSpec

-0.66

 للاسماء

-0.66

}{@

-0.64

تقاوى

-0.63

 تضيفلها

-0.61

 mapStateToProps

-0.60

 licorne

-0.60

"]);

-0.58

POSITIVE LOGITS

 eternal

1.93

 permanent

1.85

 forever

1.81

 Permanent

1.67

permanent

1.67

forever

1.65

 everlasting

1.62

Permanent

1.60

 Forever

1.58

 Eternal

1.54

Activations Density 0.036%

words that imply permanence or eternity

No Comments

No Known Activations