INDEX

Explanations

variations of the word "extra" and related concepts indicating additional quantity or effort

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 CommandType

-0.76

 jSON

-0.76

matitis

-0.73

 ciutat

-0.73

ponses

-0.71

 Geist

-0.70

iseaux

-0.69

 Biosciences

-0.68

 Umum

-0.68

 sœurs

-0.66

POSITIVE LOGITS

 EXTRA

1.71

 Extra

1.70

 extra

1.70

Extra

1.58

extra

1.58

EXTRA

1.40

 Extras

1.37

extras

1.30

 extras

1.28

textra

1.21

Activations Density 0.087%

variations of the word "extra" and related concepts indicating additional quantity or effort

No Comments

No Known Activations