INDEX

Explanations

mentions of order and arrangement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

rawDesc

-0.61

UrlResolution

-0.57

jbl

-0.56

FromNib

-0.55

 Emin

-0.55

middels

-0.54

andaş

-0.53

нент

-0.53

rovnik

-0.53

 kasarigan

-0.52

POSITIVE LOGITS

顺序

0.86

 Reihenfolge

0.83

 order

0.75

 ordem

0.73

 sequence

0.72

SEQUENCE

0.70

순

0.70

sequence

0.70

order

0.68

 ordine

0.67

Activations Density 0.495%

mentions of order and arrangement in various contexts

No Comments

No Known Activations