INDEX

Explanations

references to storage devices, particularly disks and drives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

UnusedPrivate

-0.70

 متعلقه

-0.69

 Roskov

-0.65

Personensuche

-0.64

ArgumentParser

-0.64

AEC

-0.63

__*/

-0.60

 Salah

-0.60

 ProtoMessage

-0.59

unmodifiable

-0.58

POSITIVE LOGITS

 disk

3.11

 disc

3.07

 Disk

2.89

 discs

2.80

 Disc

2.77

 disks

2.77

disk

2.75

Disk

2.68

Disc

2.53

disc

2.52

Activations Density 0.089%

references to storage devices, particularly disks and drives

No Comments

No Known Activations