INDEX

Explanations

terms related to hierarchical structures or nested data elements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jefus

-0.98

 Monfieur

-0.96

Efq

-0.91

 myſelf

-0.90

 himſelf

-0.87

 Shakspeare

-0.87

 themſelves

-0.86

 Houſe

-0.86

 Theſe

-0.85

 Majefty

-0.84

POSITIVE LOGITS

child

0.93

providedIn

0.83

PageRoute

0.79

 StatelessWidget

0.77

 StatefulWidget

0.76

awtextra

0.73

writerow

0.70

 consultato

0.68

cshtml

0.68

runApp

0.67

Activations Density 0.013%

terms related to hierarchical structures or nested data elements

No Comments

No Known Activations