INDEX

Explanations

key programming terms and structures related to configuration settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 autorytatywna

-0.87

 protoimpl

-0.83

GEBURTSDATUM

-0.79

setVerticalGroup

-0.76

 cherchés

-0.73

 ModelExpression

-0.72

QMetaType

-0.70

EndGlobalSection

-0.69

AnchorStyles

-0.67

RenderAtEndOf

-0.66

POSITIVE LOGITS

 default

3.52

default

3.14

 Default

2.66

Default

2.61

 defaults

2.29

默认

2.27

 DEFAULT

2.15

 defaulted

2.12

DEFAULT

2.10

デフォ

1.94

Activations Density 0.270%

key programming terms and structures related to configuration settings

No Comments

No Known Activations