INDEX

Explanations

characters, formatting, and dimensions in code structures or markup

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Size

-0.99

size

-0.94

 size

-0.91

 Size

-0.86

 sizes

-0.79

sizes

-0.71

 SIZE

-0.71

 Sizes

-0.69

Sizes

-0.68

SIZE

-0.67

POSITIVE LOGITS

DockStyle

1.30

ContentAsync

0.99

 EconPapers

0.98

хьтан

0.92

 disambiguazione

0.88

Rohy

0.85

 الرياضيه

0.82

 nahilalakip

0.82

ConstraintMaker

0.81

 NSCoder

0.81

Activations Density 0.240%

characters, formatting, and dimensions in code structures or markup

No Comments

No Known Activations