INDEX

Explanations

terms related to quality and characteristics of products or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 MonoBehaviour

-0.88

fois

-0.62

xtext

-0.59

andReturn

-0.59

 chré

-0.57

 liné

-0.57

 quæ

-0.56

 Meksiku

-0.56

󠁢

-0.55

 morire

-0.55

POSITIVE LOGITS

juicy

0.72

 blew

0.67

 blow

0.63

 blown

0.62

ormány

0.61

 breathe

0.60

']}

0.59

contentLoaded

0.57

top

0.57

 inaugural

0.57

Activations Density 0.710%

terms related to quality and characteristics of products or experiences

No Comments

No Known Activations