INDEX

Explanations

phrases or instructions related to user interface interactions and settings configuration

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

您

-1.03

 vostro

-1.01

 usted

-0.94

 vostri

-0.94

如果您

-0.93

 Ihnen

-0.93

您可以

-0.92

 vostra

-0.92

 Ihrer

-0.90

 vostre

-0.90

POSITIVE LOGITS

thy

1.21

 thou

1.20

 тво

0.94

 thyself

0.94

 thine

0.93

Thou

0.90

 Thou

0.90

 didst

0.89

 твое

0.89

 твои

0.88

Activations Density 0.181%

phrases or instructions related to user interface interactions and settings configuration

No Comments

No Known Activations