INDEX

Explanations

words related to significant events or novel occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 saites

-0.81

 censiti

-0.73

ymce

-0.72

-0.71

 հղումներ

-0.70

Nazionale

-0.70

IActionResult

-0.69

 समीक्षक

-0.67

 चीज़ों

-0.63

الحياه

-0.62

POSITIVE LOGITS

new

1.24

 nueva

1.01

 baru

1.00

new

0.99

新的

0.99

新しい

0.98

NEW

0.97

 nuevos

0.97

 nuevas

0.96

的新

0.93

Activations Density 0.223%

words related to significant events or novel occurrences

No Comments

No Known Activations