INDEX

Explanations

references to orders and the ordering process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

etheless

-0.91

rachtet

-0.90

PMG

-0.86

chequer

-0.84

cifix

-0.82

rapnel

-0.79

wixt

-0.79

 leksikon

-0.77

edicated

-0.77

phazard

-0.76

POSITIVE LOGITS

 Order

2.08

 order

2.07

 ORDER

1.98

 orders

1.98

order

1.94

 Orders

1.91

Order

1.89

ORDER

1.83

orders

1.71

Orders

1.65

Activations Density 0.088%

references to orders and the ordering process

No Comments

No Known Activations