INDEX

Explanations

references to crises or emergencies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enna

-0.66

Gu

-0.66

Sni

-0.65

 Arter

-0.64

 خارجية

-0.64

 Enzy

-0.64

tickets

-0.63

Gene

-0.63

び

-0.63

 artistic

-0.63

POSITIVE LOGITS

 crisis

1.07

 crises

0.91

Amicalement

0.90

intenance

0.90

 crisi

0.89

Crisis

0.88

crisis

0.85

 Crisis

0.82

NSNotification

0.80

 crise

0.80

Activations Density 0.137%

references to crises or emergencies

No Comments

No Known Activations