INDEX

Explanations

references to infinite quantities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 चीज़ों

-0.77

hoeddwyd

-0.64

 Roskov

-0.62

LabelTagHelper

-0.62

出版年

-0.61

 TextAppearance

-0.59

 ویکی‌پدی

-0.59

parsedMessage

-0.58

dig

-0.58

Composable

-0.56

POSITIVE LOGITS

 infinite

0.79

 unlimited

0.75

 infinita

0.72

 infinitely

0.71

 limitless

0.70

 ilimit

0.69

 Infinite

0.68

infinite

0.68

 illimit

0.65

 infinit

0.62

Activations Density 2.082%

references to infinite quantities or concepts

No Comments

No Known Activations