INDEX

Explanations

references to different types of UI elements and their properties in coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ModelAdmin

-0.94

 pleaſure

-0.91

withstanding

-0.89

 Majefty

-0.80

 secondaires

-0.80

 ſtill

-0.78

PerformLayout

-0.77

 himſelf

-0.76

DSA

-0.74

 onCancelled

-0.74

POSITIVE LOGITS

box

2.73

Box

2.63

box

2.52

BOX

2.51

 boxes

2.49

Box

2.35

BOX

2.35

 Boxes

2.24

boxes

2.21

Boxes

1.90

Activations Density 0.114%

references to different types of UI elements and their properties in coding contexts

No Comments

No Known Activations