INDEX

Explanations

mentions of time-related terms and phrases, particularly those referencing the present or recent past

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 للاسماء

-0.85

 nahilalakip

-0.70

jalá

-0.67

Personendaten

-0.66

 comprends

-0.66

InjectAttribute

-0.64

 venait

-0.64

 خارجية

-0.63

ьаж

-0.62

 Josephus

-0.62

POSITIVE LOGITS

 modern

1.10

modern

0.93

 moderne

0.92

Nowadays

0.92

Modern

0.86

 Modern

0.85

現代

0.84

 nowadays

0.83

 moderna

0.81

 MODERN

0.81

Activations Density 0.205%

mentions of time-related terms and phrases, particularly those referencing the present or recent past

No Comments

No Known Activations