INDEX

Explanations

references to items in a data structure or list

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 GenerationType

-1.06

 Мексичка

-0.88

GraphicsUnit

-0.87

PerformLayout

-0.83

EnableWeb

-0.81

BagLayout

-0.80

UnusedPrivate

-0.79

 Hough

-0.76

SaveChanges

-0.76

 Continu

-0.73

POSITIVE LOGITS

 ITEM

1.45

 items

1.44

 Item

1.44

 Items

1.41

 item

1.40

items

1.35

 ITEMS

1.34

Item

1.21

Items

1.18

ITEM

1.15

Activations Density 0.024%

references to items in a data structure or list

No Comments

No Known Activations