INDEX

Explanations

references to convenience and ease-of-use in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 تانيه

-0.74

 arşivlendi

-0.72

 שוליים

-0.72

 quæ

-0.70

 ostavi

-0.70

rungsseite

-0.68

 linkovi

-0.66

Specifiche

-0.64

Trama

-0.64

tymologie

-0.64

POSITIVE LOGITS

 neat

1.20

convenient

1.19

 neatly

1.09

 convenient

1.08

Convenient

0.99

 Convenience

0.96

 conveniently

0.96

 convenience

0.96

 Convenient

0.93

 Neat

0.92

Activations Density 0.091%

references to convenience and ease-of-use in various contexts

No Comments

No Known Activations